Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4292 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.6219. Min Act: -0.1700
Data Index: 939412 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.5594. Min Act: -0.1700
Data Index: 7199684 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.5281. Min Act: -0.1700
Data Index: 939411 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.5281. Min Act: -0.1700
Data Index: 939414 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4969. Min Act: -0.1700
Data Index: 939413 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4656. Min Act: -0.1700
Data Index: 939416 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4344. Min Act: -0.1700
Data Index: 7199683 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4344. Min Act: -0.1700
Data Index: 939417 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1566787 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2758494 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4031. Min Act: -0.1700
Data Index: 4909856 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2068853 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.4031. Min Act: -0.1700
Data Index: 4909855 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3719. Min Act: -0.1700
Data Index: 5446022 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3719. Min Act: -0.1700
Data Index: 6339921 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3719. Min Act: -0.1700
Data Index: 1552120 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3406. Min Act: -0.1700
Data Index: 1379805 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3406. Min Act: -0.1700
Data Index: 3996251 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3406. Min Act: -0.1700
Data Index: 4200743 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6219. Min Range: -4.6219
Max Act: 4.3094. Min Act: -0.1700
Data Index: 593344 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19