Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.8227. Min Act: -0.1700
Data Index: 2697498 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.7914. Min Act: -0.1700
Data Index: 3832738 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6977. Min Act: -0.1700
Data Index: 4187638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.7289. Min Act: -0.1700
Data Index: 5342090 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 1310308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2923216 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 944896 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2923215 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 6087918 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6039. Min Act: -0.1700
Data Index: 6884406 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6039. Min Act: -0.1700
Data Index: 1678779 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6039. Min Act: -0.1700
Data Index: 5609480 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6039. Min Act: -0.1699
Data Index: 8739046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6039. Min Act: -0.1700
Data Index: 3015960 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4801573 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 8533794 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 7886461 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 1142693 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 1929465 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.5727. Min Act: -0.1700
Data Index: 209349 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19