Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 692 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.3204. Min Act: -0.1700
Data Index: 7820670 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.1329. Min Act: -0.1700
Data Index: 7119431 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.1329. Min Act: -0.1700
Data Index: 2816744 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.1329. Min Act: -0.1700
Data Index: 2742190 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.1016. Min Act: -0.1700
Data Index: 3384960 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0704. Min Act: -0.1700
Data Index: 4361472 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0704. Min Act: -0.1700
Data Index: 3127278 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0704. Min Act: -0.1700
Data Index: 3560218 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0704. Min Act: -0.1700
Data Index: 3958477 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0391. Min Act: -0.1700
Data Index: 820041 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0079. Min Act: -0.1700
Data Index: 6430378 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0079. Min Act: -0.1700
Data Index: 316800 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0079. Min Act: -0.1700
Data Index: 6984455 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0079. Min Act: -0.1700
Data Index: 2226040 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3204. Min Range: -5.3204
Max Act: 5.0079. Min Act: -0.1700
Data Index: 2458086 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3204. Min Range: -5.3204
Max Act: 4.9766. Min Act: -0.1700
Data Index: 342808 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3204. Min Range: -5.3204
Max Act: 4.9766. Min Act: -0.1700
Data Index: 3805343 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3204. Min Range: -5.3204
Max Act: 4.9454. Min Act: -0.1700
Data Index: 6770135 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3204. Min Range: -5.3204
Max Act: 4.9454. Min Act: -0.1700
Data Index: 5414724 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3204. Min Range: -5.3204
Max Act: 4.9454. Min Act: -0.1700
Data Index: 6754894 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19