Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0161. Min Range: -8.0161
Max Act: 8.0161. Min Act: -0.1700
Data Index: 8813438 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.9849. Min Act: -0.1700
Data Index: 4902796 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.8911. Min Act: -0.1700
Data Index: 2070389 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.8286. Min Act: -0.1700
Data Index: 2419488 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.8286. Min Act: -0.1700
Data Index: 5669819 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.8286. Min Act: -0.1700
Data Index: 1251214 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.8286. Min Act: -0.1700
Data Index: 7309410 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7974. Min Act: -0.1700
Data Index: 1708771 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7661. Min Act: -0.1700
Data Index: 7207751 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7661. Min Act: -0.1700
Data Index: 4016351 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7349. Min Act: -0.1700
Data Index: 5247864 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7349. Min Act: -0.1700
Data Index: 5844896 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7349. Min Act: -0.1700
Data Index: 2527058 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7036. Min Act: -0.1700
Data Index: 1440984 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7661. Min Act: -0.1700
Data Index: 7066188 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7036. Min Act: -0.1700
Data Index: 336070 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7036. Min Act: -0.1700
Data Index: 4172417 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.7036. Min Act: -0.1700
Data Index: 8780259 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.6724. Min Act: -0.1700
Data Index: 2724402 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0161. Min Range: -8.0161
Max Act: 7.6724. Min Act: -0.1700
Data Index: 431290 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19