Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.9467. Min Act: -0.1700
Data Index: 5311429 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.9155. Min Act: -0.1700
Data Index: 1693554 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.8842. Min Act: -0.1700
Data Index: 306624 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.8842. Min Act: -0.1700
Data Index: 4660580 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7905. Min Act: -0.1700
Data Index: 3478457 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7280. Min Act: -0.1700
Data Index: 3940674 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7280. Min Act: -0.1700
Data Index: 2818646 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7280. Min Act: -0.1700
Data Index: 7219721 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7592. Min Act: -0.1700
Data Index: 3746554 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6655. Min Act: -0.1700
Data Index: 3640919 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.7280. Min Act: -0.1700
Data Index: 4788 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6967. Min Act: -0.1700
Data Index: 2436498 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6342. Min Act: -0.1700
Data Index: 7022490 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6030. Min Act: -0.1700
Data Index: 6038732 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6342. Min Act: -0.1700
Data Index: 7144133 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6342. Min Act: -0.1700
Data Index: 3903848 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1190045 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6030. Min Act: -0.1700
Data Index: 2927187 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.6342. Min Act: -0.1700
Data Index: 6221628 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9467. Min Range: -6.9467
Max Act: 6.5717. Min Act: -0.1700
Data Index: 2048856 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19