Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.7095. Min Act: -0.1690
Data Index: 4524927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6487. Min Act: -0.1700
Data Index: 1984993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6226. Min Act: -0.1700
Data Index: 5852820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5702. Min Act: -0.1700
Data Index: 7837606 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5615. Min Act: -0.1689
Data Index: 2385906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5264. Min Act: -0.1698
Data Index: 7772984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5352. Min Act: -0.1700
Data Index: 594393 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5352. Min Act: -0.1700
Data Index: 8258577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5264. Min Act: -0.1700
Data Index: 2315969 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1692
Data Index: 4802936 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1685
Data Index: 4802944 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5089. Min Act: -0.1700
Data Index: 813460 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5089. Min Act: -0.1696
Data Index: 4802938 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1680
Data Index: 4802937 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1700
Data Index: 7639818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1700
Data Index: 6901338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1611
Data Index: 4802942 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.4913. Min Act: -0.1700
Data Index: 5484719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.4913. Min Act: -0.1599
Data Index: 4802939 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.4913. Min Act: -0.1640
Data Index: 4802943 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19