Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.4760. Min Act: -0.1700
Data Index: 5021213 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.2885. Min Act: -0.1700
Data Index: 5151751 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.2260. Min Act: -0.1700
Data Index: 6006382 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.2885. Min Act: -0.1700
Data Index: 8635601 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.2260. Min Act: -0.1700
Data Index: 8709358 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.1010. Min Act: -0.1700
Data Index: 5109986 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.1010. Min Act: -0.1700
Data Index: 6394416 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.1010. Min Act: -0.1700
Data Index: 8371045 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.1010. Min Act: -0.1700
Data Index: 1640005 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.1010. Min Act: -0.1700
Data Index: 5443911 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.9760. Min Act: -0.1700
Data Index: 2829762 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.0385. Min Act: -0.1700
Data Index: 764825 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.0385. Min Act: -0.1700
Data Index: 2741389 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.9760. Min Act: -0.1700
Data Index: 8514813 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.0385. Min Act: -0.1700
Data Index: 5962891 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4760. Min Range: -11.4760
Max Act: 11.0385. Min Act: -0.1700
Data Index: 605871 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.8510. Min Act: -0.1700
Data Index: 3504032 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.9760. Min Act: -0.1700
Data Index: 2724034 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.9760. Min Act: -0.1700
Data Index: 988002 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4760. Min Range: -11.4760
Max Act: 10.9760. Min Act: -0.1700
Data Index: 2798684 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19