Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.9390. Min Act: -0.1700
Data Index: 7129421 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.8140. Min Act: -0.1700
Data Index: 2619476 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.7515. Min Act: -0.1700
Data Index: 7325197 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.7202. Min Act: -0.1700
Data Index: 8109190 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.6265. Min Act: -0.1700
Data Index: 7599758 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.6265. Min Act: -0.1700
Data Index: 3517398 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5015. Min Act: -0.1700
Data Index: 234689 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5327. Min Act: -0.1700
Data Index: 2231876 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5327. Min Act: -0.1700
Data Index: 7564363 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5327. Min Act: -0.1700
Data Index: 5649065 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4390. Min Act: -0.1700
Data Index: 7300734 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4077. Min Act: -0.1700
Data Index: 2943084 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4390. Min Act: -0.1700
Data Index: 751629 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4077. Min Act: -0.1700
Data Index: 5748497 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.3140. Min Act: -0.1700
Data Index: 2704721 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1261910 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.3140. Min Act: -0.1700
Data Index: 4162239 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.2827. Min Act: -0.1700
Data Index: 3277313 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.2515. Min Act: -0.1700
Data Index: 3527192 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.2202. Min Act: -0.1700
Data Index: 4190186 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19