Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6592. Min Range: -9.6592
Max Act: 9.6592. Min Act: -0.1700
Data Index: 6103904 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6592. Min Range: -9.6592
Max Act: 9.2217. Min Act: -0.1700
Data Index: 4726800 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6592. Min Range: -9.6592
Max Act: 9.1592. Min Act: -0.1700
Data Index: 7745130 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6592. Min Range: -9.6592
Max Act: 9.0967. Min Act: -0.1700
Data Index: 1540120 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.9717. Min Act: -0.1700
Data Index: 2334028 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.8155. Min Act: -0.1700
Data Index: 3992774 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.6905. Min Act: -0.1700
Data Index: 5679953 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.7217. Min Act: -0.1700
Data Index: 4475698 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.6592. Min Act: -0.1700
Data Index: 613348 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.6280. Min Act: -0.1700
Data Index: 719367 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.6592. Min Act: -0.1700
Data Index: 613353 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5655. Min Act: -0.1700
Data Index: 8219142 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5655. Min Act: -0.1700
Data Index: 5679956 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5655. Min Act: -0.1700
Data Index: 7090938 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5342. Min Act: -0.1700
Data Index: 3226767 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5342. Min Act: -0.1700
Data Index: 7422193 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.5030. Min Act: -0.1700
Data Index: 4899727 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.4717. Min Act: -0.1700
Data Index: 613346 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.4717. Min Act: -0.1700
Data Index: 879617 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6592. Min Range: -9.6592
Max Act: 8.3780. Min Act: -0.1700
Data Index: 5806076 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19