Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2136 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.9087. Min Act: -0.1700
Data Index: 2657503 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1615884 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.9087. Min Act: -0.1700
Data Index: 3120725 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.9087. Min Act: -0.1700
Data Index: 983525 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8929. Min Act: -0.1700
Data Index: 3876650 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8611. Min Act: -0.1700
Data Index: 446619 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8611. Min Act: -0.1700
Data Index: 6296288 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8611. Min Act: -0.1700
Data Index: 5529619 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8452. Min Act: -0.1700
Data Index: 4924009 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8293. Min Act: -0.1700
Data Index: 1031908 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8293. Min Act: -0.1700
Data Index: 1800631 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.8134. Min Act: -0.1700
Data Index: 6580282 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 7015829 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 3692992 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7816. Min Act: -0.1700
Data Index: 3257455 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 239046 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7816. Min Act: -0.1700
Data Index: 5598867 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 2235325 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 460529 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9087. Min Range: -2.9087
Max Act: 2.7975. Min Act: -0.1700
Data Index: 5946969 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19