Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0003. Min Range: -7.0003
Max Act: 7.0003. Min Act: -0.1700
Data Index: 7696686 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.7190. Min Act: -0.1700
Data Index: 7696685 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.6878. Min Act: -0.1700
Data Index: 6860992 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.6253. Min Act: -0.1700
Data Index: 7039857 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.5315. Min Act: -0.1700
Data Index: 3556662 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.5315. Min Act: -0.1700
Data Index: 7696683 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.5003. Min Act: -0.1700
Data Index: 7948633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5794211 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.4378. Min Act: -0.1700
Data Index: 3038156 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.4065. Min Act: -0.1700
Data Index: 8042361 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3753. Min Act: -0.1700
Data Index: 6272498 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3753. Min Act: -0.1700
Data Index: 1536068 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3440. Min Act: -0.1700
Data Index: 1166262 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3440. Min Act: -0.1700
Data Index: 7149083 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 728824 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.2815. Min Act: -0.1700
Data Index: 728829 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 1529166 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 5417202 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 1844505 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0003. Min Range: -7.0003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 4429035 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19