Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2147. Min Range: -7.2147
Max Act: 7.2147. Min Act: -0.1700
Data Index: 6129429 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2147. Min Range: -7.2147
Max Act: 7.1210. Min Act: -0.1700
Data Index: 700473 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2147. Min Range: -7.2147
Max Act: 7.0585. Min Act: -0.1700
Data Index: 8668478 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2147. Min Range: -7.2147
Max Act: 7.0272. Min Act: -0.1700
Data Index: 8636052 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9647. Min Act: -0.1700
Data Index: 3502881 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9647. Min Act: -0.1700
Data Index: 4617332 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9647. Min Act: -0.1700
Data Index: 1007986 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9022. Min Act: -0.1700
Data Index: 2708587 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9022. Min Act: -0.1700
Data Index: 6916314 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9335. Min Act: -0.1700
Data Index: 437980 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9022. Min Act: -0.1700
Data Index: 5077926 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.9022. Min Act: -0.1700
Data Index: 7031322 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8710. Min Act: -0.1700
Data Index: 7940608 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8710. Min Act: -0.1700
Data Index: 1581303 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8710. Min Act: -0.1700
Data Index: 3574462 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8397. Min Act: -0.1700
Data Index: 5749838 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8397. Min Act: -0.1700
Data Index: 337190 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8397. Min Act: -0.1700
Data Index: 721380 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8085. Min Act: -0.1700
Data Index: 2406256 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2147. Min Range: -7.2147
Max Act: 6.8085. Min Act: -0.1700
Data Index: 2715003 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19