Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4991. Min Range: -8.4991
Max Act: 8.4991. Min Act: -0.1700
Data Index: 778506 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.9054. Min Act: -0.1700
Data Index: 8165864 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.8741. Min Act: -0.1700
Data Index: 1214062 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.8741. Min Act: -0.1700
Data Index: 2279074 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.8429. Min Act: -0.1700
Data Index: 7243585 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7804. Min Act: -0.1700
Data Index: 2988631 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.8116. Min Act: -0.1700
Data Index: 184066 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.8116. Min Act: -0.1700
Data Index: 2624364 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7491. Min Act: -0.1700
Data Index: 5794872 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7179. Min Act: -0.1700
Data Index: 3212637 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7179. Min Act: -0.1700
Data Index: 2064014 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7179. Min Act: -0.1700
Data Index: 4059025 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7179. Min Act: -0.1700
Data Index: 4467010 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7179. Min Act: -0.1700
Data Index: 1092308 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.7804. Min Act: -0.1700
Data Index: 5715626 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.6241. Min Act: -0.1700
Data Index: 1180842 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.6554. Min Act: -0.1700
Data Index: 8202116 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.6866. Min Act: -0.1700
Data Index: 7526838 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.5929. Min Act: -0.1700
Data Index: 7803812 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4991. Min Range: -8.4991
Max Act: 7.6241. Min Act: -0.1700
Data Index: 6452669 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19