Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.4659. Min Range: -7.4659
Max Act: 7.4034. Min Act: -0.1700
Data Index: 2887478 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4659. Min Range: -7.4659
Max Act: 7.4659. Min Act: -0.1700
Data Index: 7495958 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4659. Min Range: -7.4659
Max Act: 7.4346. Min Act: -0.1700
Data Index: 8482259 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4659. Min Range: -7.4659
Max Act: 7.3409. Min Act: -0.1700
Data Index: 4064593 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4659. Min Range: -7.4659
Max Act: 7.2784. Min Act: -0.1700
Data Index: 3245904 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4659. Min Range: -7.4659
Max Act: 6.2471. Min Act: -0.1700
Data Index: 3534230 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4659. Min Range: -7.4659
Max Act: 6.1534. Min Act: -0.1700
Data Index: 4186727 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.9659. Min Act: -0.1700
Data Index: 2466798 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.7784. Min Act: -0.1700
Data Index: 8279592 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.8096. Min Act: -0.1700
Data Index: 7432710 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 7213381 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 2796537 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 874650 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 7213576 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6846. Min Act: -0.1700
Data Index: 7716730 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6846. Min Act: -0.1700
Data Index: 1381595 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6846. Min Act: -0.1700
Data Index: 6525356 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6221. Min Act: -0.1700
Data Index: 5572190 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6534. Min Act: -0.1700
Data Index: 4742207 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4659. Min Range: -7.4659
Max Act: 5.6221. Min Act: -0.1700
Data Index: 8076522 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19