Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5561 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0573. Min Range: -7.0573
Max Act: 7.0573. Min Act: -0.1700
Data Index: 8742341 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.9635. Min Act: -0.1700
Data Index: 4052303 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.9323. Min Act: -0.1700
Data Index: 6870714 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3510057 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.8698. Min Act: -0.1700
Data Index: 6606113 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.7448. Min Act: -0.1700
Data Index: 8330081 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.6823. Min Act: -0.1700
Data Index: 8646965 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6446106 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.6510. Min Act: -0.1700
Data Index: 6733236 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.6198. Min Act: -0.1700
Data Index: 6396211 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.6198. Min Act: -0.1700
Data Index: 6600108 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.5885. Min Act: -0.1700
Data Index: 1881760 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.5573. Min Act: -0.1700
Data Index: 1061911 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.5260. Min Act: -0.1700
Data Index: 2777318 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4948. Min Act: -0.1700
Data Index: 4006965 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4948. Min Act: -0.1700
Data Index: 8331832 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4948. Min Act: -0.1700
Data Index: 6690275 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4948. Min Act: -0.1700
Data Index: 8209184 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4635. Min Act: -0.1700
Data Index: 887271 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0573. Min Range: -7.0573
Max Act: 6.4323. Min Act: -0.1700
Data Index: 5170321 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19