Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.4587. Min Act: -0.1700
Data Index: 8358673 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.4274. Min Act: -0.1700
Data Index: 1049683 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3962. Min Act: -0.1700
Data Index: 6259379 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3024. Min Act: -0.1700
Data Index: 6959118 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3024. Min Act: -0.1700
Data Index: 2782864 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3024. Min Act: -0.1700
Data Index: 1432487 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.2399. Min Act: -0.1700
Data Index: 6377477 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.2399. Min Act: -0.1700
Data Index: 748121 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1774. Min Act: -0.1700
Data Index: 1791975 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1774. Min Act: -0.1700
Data Index: 6058782 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1774. Min Act: -0.1700
Data Index: 2834029 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1774. Min Act: -0.1700
Data Index: 4429664 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1774. Min Act: -0.1700
Data Index: 4554273 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1461. Min Act: -0.1700
Data Index: 8442556 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1461. Min Act: -0.1700
Data Index: 5544991 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1461. Min Act: -0.1700
Data Index: 3316865 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1461. Min Act: -0.1700
Data Index: 7086577 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1461. Min Act: -0.1700
Data Index: 7187655 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1149. Min Act: -0.1700
Data Index: 3070831 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.1149. Min Act: -0.1700
Data Index: 4597140 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19