Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2146 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0844. Min Range: -6.0844
Max Act: 6.0844. Min Act: -0.1700
Data Index: 3917004 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.9282. Min Act: -0.1700
Data Index: 3540729 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.8657. Min Act: -0.1700
Data Index: 3381077 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.6469. Min Act: -0.1700
Data Index: 7553445 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.6469. Min Act: -0.1700
Data Index: 5866127 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5532. Min Act: -0.1700
Data Index: 6556038 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5844. Min Act: -0.1700
Data Index: 3334992 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.6157. Min Act: -0.1700
Data Index: 1119421 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5844. Min Act: -0.1700
Data Index: 3571527 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5532. Min Act: -0.1700
Data Index: 7689060 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5219. Min Act: -0.1700
Data Index: 6889190 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5219. Min Act: -0.1700
Data Index: 1700522 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4594. Min Act: -0.1700
Data Index: 5995704 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4907. Min Act: -0.1700
Data Index: 1324740 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.5219. Min Act: -0.1700
Data Index: 4519894 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4907. Min Act: -0.1700
Data Index: 1700521 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4282. Min Act: -0.1700
Data Index: 4089609 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4282. Min Act: -0.1700
Data Index: 997637 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4282. Min Act: -0.1700
Data Index: 6792023 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0844. Min Range: -6.0844
Max Act: 5.4282. Min Act: -0.1700
Data Index: 8069997 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19