Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1178 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3258. Min Range: -4.3258
Max Act: 4.3258. Min Act: -0.1700
Data Index: 4984812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3258. Min Range: -4.3258
Max Act: 4.3258. Min Act: -0.1700
Data Index: 1193861 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3258. Min Range: -4.3258
Max Act: 4.0757. Min Act: -0.1700
Data Index: 7244345 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3258. Min Range: -4.3258
Max Act: 4.0445. Min Act: -0.1700
Data Index: 8219722 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.9194. Min Act: -0.1700
Data Index: 1618316 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.8256. Min Act: -0.1700
Data Index: 4627951 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7631. Min Act: -0.1700
Data Index: 4094288 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7631. Min Act: -0.1700
Data Index: 1058976 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7943. Min Act: -0.1700
Data Index: 8489422 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7943. Min Act: -0.1700
Data Index: 4678190 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7318. Min Act: -0.1700
Data Index: 7580275 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7318. Min Act: -0.1700
Data Index: 2715903 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7318. Min Act: -0.1700
Data Index: 1994858 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7318. Min Act: -0.1700
Data Index: 6018268 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.6692. Min Act: -0.1700
Data Index: 8164846 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7005. Min Act: -0.1700
Data Index: 7182119 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7005. Min Act: -0.1700
Data Index: 3485857 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7005. Min Act: -0.1700
Data Index: 3695727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7005. Min Act: -0.1700
Data Index: 4535190 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3258. Min Range: -4.3258
Max Act: 3.7005. Min Act: -0.1700
Data Index: 1295233 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19