Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.5605. Min Act: -0.1700
Data Index: 2001978 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.5292. Min Act: -0.1700
Data Index: 2302342 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4980. Min Act: -0.1700
Data Index: 5073317 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4980. Min Act: -0.1700
Data Index: 7759476 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4667. Min Act: -0.1700
Data Index: 2339867 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4355. Min Act: -0.1700
Data Index: 1464490 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4667. Min Act: -0.1700
Data Index: 2727463 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4355. Min Act: -0.1700
Data Index: 3796737 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4355. Min Act: -0.1700
Data Index: 6450566 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4355. Min Act: -0.1700
Data Index: 4987399 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4355. Min Act: -0.1700
Data Index: 822988 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4042. Min Act: -0.1700
Data Index: 1116046 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4042. Min Act: -0.1700
Data Index: 6776346 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4042. Min Act: -0.1700
Data Index: 2575395 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.4042. Min Act: -0.1700
Data Index: 1967820 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.3730. Min Act: -0.1700
Data Index: 2682042 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.3730. Min Act: -0.1700
Data Index: 530796 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.3417. Min Act: -0.1700
Data Index: 1639905 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.3417. Min Act: -0.1700
Data Index: 3046693 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5605. Min Range: -4.5605
Max Act: 4.3730. Min Act: -0.1700
Data Index: 7656270 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19