Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 15.1193. Min Range: -15.1193
Max Act: 15.1193. Min Act: -0.1700
Data Index: 6232271 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1193. Min Range: -15.1193
Max Act: 11.5568. Min Act: -0.1700
Data Index: 655450 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.9943. Min Act: -0.1700
Data Index: 8700325 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.9318. Min Act: -0.1700
Data Index: 133615 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.8068. Min Act: -0.1700
Data Index: 3680788 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.8693. Min Act: -0.1700
Data Index: 4998041 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.5568. Min Act: -0.1700
Data Index: 394629 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.5568. Min Act: -0.1700
Data Index: 2387204 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.4943. Min Act: -0.1700
Data Index: 7866636 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.4943. Min Act: -0.1700
Data Index: 290431 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.1818. Min Act: -0.1700
Data Index: 4294113 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1193. Min Range: -15.1193
Max Act: 14.1818. Min Act: -0.1700
Data Index: 1453974 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.9943. Min Act: -0.1700
Data Index: 3891481 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1193. Min Range: -15.1193
Max Act: 10.9318. Min Act: -0.1700
Data Index: 7679963 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.8693. Min Act: -0.1700
Data Index: 6047151 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.8693. Min Act: -0.1700
Data Index: 3276150 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.9318. Min Act: -0.1700
Data Index: 3489407 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.8693. Min Act: -0.1700
Data Index: 3575151 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.8068. Min Act: -0.1700
Data Index: 7743442 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1193. Min Range: -15.1193
Max Act: 13.6193. Min Act: -0.1700
Data Index: 2330189 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19