Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6345 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6706. Min Range: -7.6706
Max Act: 7.6706. Min Act: -0.1700
Data Index: 8578109 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6706. Min Range: -7.6706
Max Act: 7.2019. Min Act: -0.1700
Data Index: 7772322 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.9206. Min Act: -0.1700
Data Index: 1976965 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.9206. Min Act: -0.1700
Data Index: 899999 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.8269. Min Act: -0.1700
Data Index: 1881525 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.7956. Min Act: -0.1700
Data Index: 6775772 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.7331. Min Act: -0.1700
Data Index: 5221879 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.7019. Min Act: -0.1700
Data Index: 6471699 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.7019. Min Act: -0.1700
Data Index: 5552767 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.7019. Min Act: -0.1700
Data Index: 8812972 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.6706. Min Act: -0.1700
Data Index: 7081893 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.6706. Min Act: -0.1700
Data Index: 5512717 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.6394. Min Act: -0.1700
Data Index: 433673 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.6394. Min Act: -0.1700
Data Index: 1174258 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.6081. Min Act: -0.1700
Data Index: 4731265 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.5769. Min Act: -0.1700
Data Index: 5001359 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.5769. Min Act: -0.1700
Data Index: 8580791 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.5769. Min Act: -0.1700
Data Index: 2669626 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.5456. Min Act: -0.1700
Data Index: 1859455 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6706. Min Range: -7.6706
Max Act: 6.5456. Min Act: -0.1700
Data Index: 1916507 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19