Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.8035. Min Act: -0.1700
Data Index: 4045623 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.6160. Min Act: -0.1700
Data Index: 5013160 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.6160. Min Act: -0.1699
Data Index: 4621659 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.5535. Min Act: -0.1700
Data Index: 1081142 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.5535. Min Act: -0.1700
Data Index: 8111879 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.5223. Min Act: -0.1700
Data Index: 2465552 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.5223. Min Act: -0.1700
Data Index: 6986832 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.5223. Min Act: -0.1700
Data Index: 7865804 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4910. Min Act: -0.1700
Data Index: 2134216 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4910. Min Act: -0.1700
Data Index: 5081979 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4910. Min Act: -0.1700
Data Index: 3417804 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4910. Min Act: -0.1700
Data Index: 4393510 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4598. Min Act: -0.1700
Data Index: 3192896 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4598. Min Act: -0.1699
Data Index: 4603810 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4598. Min Act: -0.1700
Data Index: 8253009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4598. Min Act: -0.1700
Data Index: 1842218 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4598. Min Act: -0.1700
Data Index: 7082664 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4285. Min Act: -0.1700
Data Index: 2325095 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4285. Min Act: -0.1700
Data Index: 2345382 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8035. Min Range: -5.8035
Max Act: 5.4285. Min Act: -0.1700
Data Index: 3212398 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19