Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.9075. Min Act: -0.1700
Data Index: 1179118 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.8763. Min Act: -0.1700
Data Index: 7685182 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.8763. Min Act: -0.1700
Data Index: 104759 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.8763. Min Act: -0.1700
Data Index: 1255788 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.8138. Min Act: -0.1700
Data Index: 8337102 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.7825. Min Act: -0.1700
Data Index: 2536042 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.7825. Min Act: -0.1700
Data Index: 7953908 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.7200. Min Act: -0.1700
Data Index: 6492136 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6888. Min Act: -0.1700
Data Index: 578148 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6888. Min Act: -0.1700
Data Index: 2619950 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6575. Min Act: -0.1700
Data Index: 7789036 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6263. Min Act: -0.1700
Data Index: 4020321 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6263. Min Act: -0.1700
Data Index: 4271715 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5950. Min Act: -0.1700
Data Index: 6910938 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.6263. Min Act: -0.1700
Data Index: 6399603 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5638. Min Act: -0.1700
Data Index: 648419 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5950. Min Act: -0.1700
Data Index: 4766727 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5638. Min Act: -0.1700
Data Index: 3485095 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5638. Min Act: -0.1700
Data Index: 2908899 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9075. Min Range: -6.9075
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2595187 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19