Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2965. Min Act: -0.1700
Data Index: 227524 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2965. Min Act: -0.1700
Data Index: 8417394 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2652. Min Act: -0.1700
Data Index: 5290562 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 2338209 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 6768442 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 2839111 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 3044668 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2340. Min Act: -0.1700
Data Index: 4433737 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 3751759 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 3413414 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 4637345 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 5072754 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 7432537 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1698
Data Index: 4119300 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 4679017 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 6989564 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.2027. Min Act: -0.1700
Data Index: 355891 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 1219676 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 227527 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2965. Min Range: -6.2965
Max Act: 6.1715. Min Act: -0.1700
Data Index: 2144835 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19