Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.8640. Min Act: -0.1700
Data Index: 3361742 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.8640. Min Act: -0.1700
Data Index: 3361727 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.4577. Min Act: -0.1700
Data Index: 4627559 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.4577. Min Act: -0.1700
Data Index: 6048705 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.3952. Min Act: -0.1700
Data Index: 8273168 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.3327. Min Act: -0.1700
Data Index: 1263964 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.3327. Min Act: -0.1700
Data Index: 6828290 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.1765. Min Act: -0.1700
Data Index: 6536904 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.1452. Min Act: -0.1700
Data Index: 5286343 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.1140. Min Act: -0.1700
Data Index: 3981599 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0827. Min Act: -0.1700
Data Index: 7653099 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.1140. Min Act: -0.1700
Data Index: 7316284 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0515. Min Act: -0.1700
Data Index: 4880358 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0827. Min Act: -0.1700
Data Index: 5820863 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0515. Min Act: -0.1700
Data Index: 7511210 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0515. Min Act: -0.1700
Data Index: 3841030 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8640. Min Range: -7.8640
Max Act: 7.0515. Min Act: -0.1700
Data Index: 7533506 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8640. Min Range: -7.8640
Max Act: 6.9890. Min Act: -0.1700
Data Index: 4119745 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8640. Min Range: -7.8640
Max Act: 6.9890. Min Act: -0.1700
Data Index: 3114750 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8640. Min Range: -7.8640
Max Act: 6.9577. Min Act: -0.1700
Data Index: 2534006 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19