Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.8869. Min Act: -0.1700
Data Index: 383486 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.8557. Min Act: -0.1700
Data Index: 8198798 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.8557. Min Act: -0.1700
Data Index: 1736624 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7619. Min Act: -0.1700
Data Index: 2147712 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7932. Min Act: -0.1700
Data Index: 5861282 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.8557. Min Act: -0.1700
Data Index: 3606760 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7619. Min Act: -0.1700
Data Index: 8527551 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7307. Min Act: -0.1700
Data Index: 5148666 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7619. Min Act: -0.1700
Data Index: 8165987 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.7932. Min Act: -0.1700
Data Index: 3771503 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6369. Min Act: -0.1700
Data Index: 5329238 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6369. Min Act: -0.1700
Data Index: 357866 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.5744. Min Act: -0.1700
Data Index: 2180399 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6682. Min Act: -0.1700
Data Index: 1635628 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6369. Min Act: -0.1700
Data Index: 5513942 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6682. Min Act: -0.1700
Data Index: 8198799 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6369. Min Act: -0.1700
Data Index: 6830698 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6057. Min Act: -0.1700
Data Index: 4996669 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.5744. Min Act: -0.1700
Data Index: 8137038 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8869. Min Range: -7.8869
Max Act: 7.6369. Min Act: -0.1700
Data Index: 5774954 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19