Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5030. Min Range: -8.5030
Max Act: 8.5030. Min Act: -0.1700
Data Index: 4007931 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5030. Min Range: -8.5030
Max Act: 8.4405. Min Act: -0.1700
Data Index: 6960814 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5030. Min Range: -8.5030
Max Act: 8.3155. Min Act: -0.1700
Data Index: 493096 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.9405. Min Act: -0.1700
Data Index: 143923 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.9405. Min Act: -0.1700
Data Index: 3384460 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5030. Min Range: -8.5030
Max Act: 8.0655. Min Act: -0.1700
Data Index: 2357715 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5030. Min Range: -8.5030
Max Act: 8.0030. Min Act: -0.1700
Data Index: 362688 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8780. Min Act: -0.1700
Data Index: 6519860 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8780. Min Act: -0.1700
Data Index: 4770850 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 4158815 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 4378432 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 7974761 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 8782875 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 5744081 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 5671559 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7217. Min Act: -0.1700
Data Index: 3068774 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.8155. Min Act: -0.1700
Data Index: 4970294 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 3475889 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7530. Min Act: -0.1700
Data Index: 6088913 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5030. Min Range: -8.5030
Max Act: 7.7217. Min Act: -0.1700
Data Index: 7567352 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19