Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.6711. Min Act: -0.1700
Data Index: 8288453 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5772. Min Act: -0.1700
Data Index: 5841899 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5616. Min Act: -0.1700
Data Index: 29150 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5459. Min Act: -0.1700
Data Index: 6253354 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5459. Min Act: -0.1700
Data Index: 1958275 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5459. Min Act: -0.1700
Data Index: 3874910 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.5303. Min Act: -0.1700
Data Index: 4739140 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4833. Min Act: -0.1700
Data Index: 8547594 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4833. Min Act: -0.1700
Data Index: 1998450 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4833. Min Act: -0.1700
Data Index: 8547605 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 5927014 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 4474314 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 5818779 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 114285 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4363. Min Act: -0.1700
Data Index: 2593360 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4363. Min Act: -0.1700
Data Index: 2968342 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4520. Min Act: -0.1700
Data Index: 385772 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4363. Min Act: -0.1700
Data Index: 4258295 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 4543783 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6711. Min Range: -3.6711
Max Act: 3.4676. Min Act: -0.1700
Data Index: 6443431 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19