Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.6431. Min Act: -0.1700
Data Index: 208686 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.6118. Min Act: -0.1700
Data Index: 3551860 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.6118. Min Act: -0.1700
Data Index: 1179566 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.5493. Min Act: -0.1700
Data Index: 2181731 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.5181. Min Act: -0.1700
Data Index: 15820 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.4556. Min Act: -0.1700
Data Index: 6965808 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.4243. Min Act: -0.1700
Data Index: 6781509 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.4243. Min Act: -0.1700
Data Index: 3432478 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.4243. Min Act: -0.1700
Data Index: 2753318 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.4243. Min Act: -0.1700
Data Index: 6500478 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.3618. Min Act: -0.1700
Data Index: 4738786 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.3618. Min Act: -0.1700
Data Index: 1024462 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.3306. Min Act: -0.1700
Data Index: 358451 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.3306. Min Act: -0.1700
Data Index: 7010373 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 6596063 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 7354738 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 292626 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 6472791 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 592869 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6431. Min Range: -6.6431
Max Act: 6.2993. Min Act: -0.1700
Data Index: 1749532 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19