Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0359. Min Range: -5.0359
Max Act: 5.0359. Min Act: -0.1700
Data Index: 4668190 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0359. Min Range: -5.0359
Max Act: 5.0046. Min Act: -0.1700
Data Index: 4484886 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0359. Min Range: -5.0359
Max Act: 5.0046. Min Act: -0.1700
Data Index: 8386218 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0359. Min Range: -5.0359
Max Act: 5.0046. Min Act: -0.1700
Data Index: 6763584 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3528938 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9421. Min Act: -0.1700
Data Index: 1662777 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9421. Min Act: -0.1700
Data Index: 6177176 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9734. Min Act: -0.1700
Data Index: 8608899 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9421. Min Act: -0.1700
Data Index: 8704636 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9109. Min Act: -0.1700
Data Index: 6544541 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9421. Min Act: -0.1700
Data Index: 2822565 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.8796. Min Act: -0.1700
Data Index: 6091048 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9109. Min Act: -0.1700
Data Index: 4229505 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.9109. Min Act: -0.1700
Data Index: 452168 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.8796. Min Act: -0.1700
Data Index: 5394697 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.8484. Min Act: -0.1700
Data Index: 1091493 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.7859. Min Act: -0.1700
Data Index: 2102395 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.7859. Min Act: -0.1700
Data Index: 6061631 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.7859. Min Act: -0.1700
Data Index: 8806697 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0359. Min Range: -5.0359
Max Act: 4.7546. Min Act: -0.1700
Data Index: 4343379 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19