Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.9940. Min Act: -0.1700
Data Index: 8792114 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.8376. Min Act: -0.1700
Data Index: 7033815 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7594. Min Act: -0.1700
Data Index: 2042102 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7594. Min Act: -0.1700
Data Index: 3991914 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7751. Min Act: -0.1700
Data Index: 5491449 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7438. Min Act: -0.1700
Data Index: 7671003 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7438. Min Act: -0.1700
Data Index: 3449548 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7438. Min Act: -0.1700
Data Index: 5212220 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7282. Min Act: -0.1700
Data Index: 2711775 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7282. Min Act: -0.1700
Data Index: 5623406 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7282. Min Act: -0.1700
Data Index: 1291031 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6969. Min Act: -0.1700
Data Index: 7475420 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6969. Min Act: -0.1700
Data Index: 307924 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.7125. Min Act: -0.1700
Data Index: 5279200 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7372864 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6812. Min Act: -0.1700
Data Index: 6629489 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6656. Min Act: -0.1700
Data Index: 7546044 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6343. Min Act: -0.1700
Data Index: 7409860 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6656. Min Act: -0.1700
Data Index: 8463953 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9940. Min Range: -3.9940
Max Act: 3.6343. Min Act: -0.1700
Data Index: 3826879 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19