Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.5948. Min Act: -0.1700
Data Index: 7665675 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.4385. Min Act: -0.1700
Data Index: 2655085 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.3760. Min Act: -0.1700
Data Index: 3558237 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.3760. Min Act: -0.1700
Data Index: 5015465 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.3135. Min Act: -0.1700
Data Index: 2077787 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.3135. Min Act: -0.1700
Data Index: 4414706 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 5212434 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 1245900 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 2128197 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 8634853 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 7216470 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2510. Min Act: -0.1700
Data Index: 4034080 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 2706088 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2510. Min Act: -0.1700
Data Index: 2093814 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2198. Min Act: -0.1700
Data Index: 7524543 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2510. Min Act: -0.1700
Data Index: 2259684 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2510. Min Act: -0.1700
Data Index: 4061027 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2198. Min Act: -0.1700
Data Index: 4017228 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2510. Min Act: -0.1700
Data Index: 3589102 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5948. Min Range: -6.5948
Max Act: 6.2198. Min Act: -0.1700
Data Index: 3478390 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19