Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7735. Min Range: -9.7735
Max Act: 9.7735. Min Act: -0.1700
Data Index: 2532058 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7735. Min Range: -9.7735
Max Act: 9.3360. Min Act: -0.1700
Data Index: 6891988 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7735. Min Range: -9.7735
Max Act: 9.0860. Min Act: -0.1700
Data Index: 6240209 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.8985. Min Act: -0.1700
Data Index: 4560914 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.8985. Min Act: -0.1700
Data Index: 7966344 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.8360. Min Act: -0.1700
Data Index: 1305899 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.8985. Min Act: -0.1700
Data Index: 219699 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.7110. Min Act: -0.1700
Data Index: 1941264 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.7110. Min Act: -0.1700
Data Index: 493438 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 8069496 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 4343944 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.6485. Min Act: -0.1700
Data Index: 3790171 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 4343942 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 5627866 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 3316641 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5860. Min Act: -0.1700
Data Index: 4549409 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5235. Min Act: -0.1700
Data Index: 7269227 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5235. Min Act: -0.1700
Data Index: 4941294 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5235. Min Act: -0.1700
Data Index: 3722768 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7735. Min Range: -9.7735
Max Act: 8.5235. Min Act: -0.1700
Data Index: 135676 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19