Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 960 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3299. Min Range: -8.3299
Max Act: 8.3299. Min Act: -0.1700
Data Index: 2525971 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3299. Min Range: -8.3299
Max Act: 8.0174. Min Act: -0.1700
Data Index: 140677 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.9549. Min Act: -0.1700
Data Index: 4313233 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.8299. Min Act: -0.1700
Data Index: 917172 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.7987. Min Act: -0.1700
Data Index: 2887889 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.7362. Min Act: -0.1700
Data Index: 7517560 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.7362. Min Act: -0.1700
Data Index: 8081147 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.7049. Min Act: -0.1700
Data Index: 1085429 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.5799. Min Act: -0.1700
Data Index: 4394167 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4862. Min Act: -0.1700
Data Index: 7426845 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4862. Min Act: -0.1700
Data Index: 105726 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4862. Min Act: -0.1700
Data Index: 6151235 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4237. Min Act: -0.1700
Data Index: 3758488 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4549. Min Act: -0.1700
Data Index: 1244844 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4237. Min Act: -0.1700
Data Index: 8482259 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4549. Min Act: -0.1700
Data Index: 2062364 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4549. Min Act: -0.1700
Data Index: 6419126 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.3924. Min Act: -0.1700
Data Index: 5385783 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.4237. Min Act: -0.1700
Data Index: 850729 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3299. Min Range: -8.3299
Max Act: 7.3924. Min Act: -0.1700
Data Index: 1848110 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19