Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8165. Min Range: -6.8165
Max Act: 6.8165. Min Act: -0.1700
Data Index: 8655416 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8165. Min Range: -6.8165
Max Act: 6.0040. Min Act: -0.1700
Data Index: 2893268 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.8790. Min Act: -0.1700
Data Index: 848914 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.8165. Min Act: -0.1700
Data Index: 1764508 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.8478. Min Act: -0.1700
Data Index: 6047629 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7853. Min Act: -0.1700
Data Index: 2493357 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3797611 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 5999595 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 4803162 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6884545 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 5391460 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 8150097 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 7913810 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 1472014 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2428223 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 817198 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2465684 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6618008 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 2855538 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8165. Min Range: -6.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2503044 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19