Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.3911. Min Act: -0.1700
Data Index: 8261646 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.3598. Min Act: -0.1700
Data Index: 5657686 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.2348. Min Act: -0.1700
Data Index: 6900771 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.1411. Min Act: -0.1700
Data Index: 2511714 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.1098. Min Act: -0.1700
Data Index: 7622474 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3355391 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4563740 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3911. Min Range: -6.3911
Max Act: 6.0161. Min Act: -0.1700
Data Index: 1650610 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.9536. Min Act: -0.1700
Data Index: 7776287 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.9223. Min Act: -0.1700
Data Index: 3021958 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.9536. Min Act: -0.1700
Data Index: 4998961 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.9536. Min Act: -0.1700
Data Index: 3521016 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 8793517 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 726059 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4840872 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4975136 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4690433 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4233554 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7348. Min Act: -0.1700
Data Index: 35008 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3911. Min Range: -6.3911
Max Act: 5.7036. Min Act: -0.1700
Data Index: 598249 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19