Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.9885. Min Act: -0.1700
Data Index: 4254377 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8635. Min Act: -0.1700
Data Index: 3326775 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8323. Min Act: -0.1700
Data Index: 5089970 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8323. Min Act: -0.1700
Data Index: 5383266 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 6381460 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 5562507 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 5131987 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.8010. Min Act: -0.1700
Data Index: 4601417 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.7698. Min Act: -0.1700
Data Index: 2561186 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.7698. Min Act: -0.1700
Data Index: 5004690 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6448. Min Act: -0.1700
Data Index: 3641049 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 6637065 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.6135. Min Act: -0.1700
Data Index: 1643389 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5823. Min Act: -0.1700
Data Index: 3050021 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 4251425 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5510. Min Act: -0.1700
Data Index: 2855938 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5198. Min Act: -0.1700
Data Index: 438372 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.5198. Min Act: -0.1700
Data Index: 7937413 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4573. Min Act: -0.1700
Data Index: 4965318 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9885. Min Range: -7.9885
Max Act: 7.4885. Min Act: -0.1700
Data Index: 3019296 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19