Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0668. Min Range: -1.0668
Max Act: 1.0668. Min Act: -0.1695
Data Index: 2851335 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0668. Min Range: -1.0668
Max Act: 1.0058. Min Act: -0.1690
Data Index: 3757435 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.9971. Min Act: -0.1699
Data Index: 5323799 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.9366. Min Act: -0.1700
Data Index: 988565 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.9109. Min Act: -0.1699
Data Index: 4204276 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.9109. Min Act: -0.1697
Data Index: 6018751 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.9109. Min Act: -0.1700
Data Index: 2637599 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8767. Min Act: -0.1698
Data Index: 559864 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8937. Min Act: -0.1699
Data Index: 6154828 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8597. Min Act: -0.1700
Data Index: 7462695 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8597. Min Act: -0.1700
Data Index: 5771353 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8682. Min Act: -0.1700
Data Index: 7826556 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8512. Min Act: -0.1700
Data Index: 3569410 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8597. Min Act: -0.1700
Data Index: 4631443 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8512. Min Act: -0.1700
Data Index: 6712174 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8343. Min Act: -0.1698
Data Index: 4047485 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8343. Min Act: -0.1698
Data Index: 6439201 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8343. Min Act: -0.1700
Data Index: 5611612 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8174. Min Act: -0.1693
Data Index: 3284000 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0668. Min Range: -1.0668
Max Act: 0.8090. Min Act: -0.1699
Data Index: 4360264 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19