Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.9588. Min Act: -0.1700
Data Index: 1218740 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.7713. Min Act: -0.1700
Data Index: 4039799 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.8338. Min Act: -0.1700
Data Index: 6362019 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.7401. Min Act: -0.1700
Data Index: 7383865 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.6151. Min Act: -0.1700
Data Index: 8806607 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.6151. Min Act: -0.1700
Data Index: 1674497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.6151. Min Act: -0.1700
Data Index: 6891735 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5526. Min Act: -0.1700
Data Index: 1680661 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5213. Min Act: -0.1700
Data Index: 3476692 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.4901. Min Act: -0.1700
Data Index: 355959 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5213. Min Act: -0.1700
Data Index: 4470598 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5213. Min Act: -0.1700
Data Index: 1994022 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5838. Min Act: -0.1700
Data Index: 5610117 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5526. Min Act: -0.1700
Data Index: 4015307 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.4901. Min Act: -0.1700
Data Index: 1541427 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5526. Min Act: -0.1700
Data Index: 5277260 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5213. Min Act: -0.1700
Data Index: 8319951 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.5838. Min Act: -0.1700
Data Index: 6231237 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.4901. Min Act: -0.1700
Data Index: 872737 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9588. Min Range: -6.9588
Max Act: 6.4901. Min Act: -0.1700
Data Index: 8319613 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19