Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.9632. Min Act: -0.1700
Data Index: 6800837 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.9319. Min Act: -0.1700
Data Index: 4192340 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1758045 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.9007. Min Act: -0.1700
Data Index: 541698 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.7132. Min Act: -0.1700
Data Index: 2695249 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.6194. Min Act: -0.1700
Data Index: 3209857 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.6507. Min Act: -0.1700
Data Index: 4094142 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.5882. Min Act: -0.1700
Data Index: 8449008 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.5257. Min Act: -0.1700
Data Index: 3929431 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4632. Min Act: -0.1700
Data Index: 186009 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4632. Min Act: -0.1700
Data Index: 5666012 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4164249 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4944. Min Act: -0.1700
Data Index: 5771816 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4632. Min Act: -0.1700
Data Index: 5392890 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3124662 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4319. Min Act: -0.1700
Data Index: 2005830 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4632. Min Act: -0.1700
Data Index: 5631341 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.4319. Min Act: -0.1700
Data Index: 987331 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2273514 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9632. Min Range: -5.9632
Max Act: 5.3694. Min Act: -0.1700
Data Index: 2882046 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19