Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5860. Min Range: -9.5860
Max Act: 9.5860. Min Act: -0.1700
Data Index: 4272699 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5860. Min Range: -9.5860
Max Act: 9.3360. Min Act: -0.1700
Data Index: 5392878 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5860. Min Range: -9.5860
Max Act: 9.0235. Min Act: -0.1700
Data Index: 4020534 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5860. Min Range: -9.5860
Max Act: 9.0235. Min Act: -0.1700
Data Index: 7702227 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.9610. Min Act: -0.1700
Data Index: 3157018 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.8985. Min Act: -0.1700
Data Index: 1104173 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.8360. Min Act: -0.1700
Data Index: 4966699 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.8360. Min Act: -0.1700
Data Index: 8571686 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.8360. Min Act: -0.1700
Data Index: 1121250 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.7735. Min Act: -0.1700
Data Index: 4853878 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.7735. Min Act: -0.1700
Data Index: 5920614 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.7110. Min Act: -0.1700
Data Index: 162861 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.7110. Min Act: -0.1700
Data Index: 2113027 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.6485. Min Act: -0.1700
Data Index: 8006044 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.6485. Min Act: -0.1700
Data Index: 377366 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.6485. Min Act: -0.1700
Data Index: 6581166 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.6485. Min Act: -0.1700
Data Index: 1313752 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.5860. Min Act: -0.1700
Data Index: 4853877 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.6485. Min Act: -0.1700
Data Index: 3636720 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5860. Min Range: -9.5860
Max Act: 8.5235. Min Act: -0.1700
Data Index: 314600 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19