Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0076. Min Range: -6.0076
Max Act: 6.0076. Min Act: -0.1700
Data Index: 5812724 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9763. Min Act: -0.1700
Data Index: 2234819 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9763. Min Act: -0.1700
Data Index: 6826477 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9138. Min Act: -0.1700
Data Index: 8018701 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9138. Min Act: -0.1700
Data Index: 8166377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 2577829 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1004599 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 6554717 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.9138. Min Act: -0.1700
Data Index: 6814897 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 4853313 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 4292890 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 8517050 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1576655 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.7888. Min Act: -0.1700
Data Index: 627613 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 4153397 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 1006004 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 7160158 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 6320210 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 2824111 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0076. Min Range: -6.0076
Max Act: 5.8201. Min Act: -0.1700
Data Index: 7210017 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19