Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 504 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.5844. Min Act: -0.1700
Data Index: 5022599 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.5844. Min Act: -0.1700
Data Index: 4688822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.3656. Min Act: -0.1700
Data Index: 4838192 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.3656. Min Act: -0.1700
Data Index: 5535836 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.3344. Min Act: -0.1700
Data Index: 8175260 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.3031. Min Act: -0.1700
Data Index: 33337 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.3031. Min Act: -0.1700
Data Index: 398195 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 8675342 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2719. Min Act: -0.1700
Data Index: 255571 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 4451599 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 8497776 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 4858798 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 6425250 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 8766882 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 2698212 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 8400535 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 2967985 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6730307 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7118127 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5844. Min Range: -5.5844
Max Act: 5.2406. Min Act: -0.1700
Data Index: 7410517 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19