Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3441. Min Range: -7.3441
Max Act: 7.3129. Min Act: -0.1700
Data Index: 8538422 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3441. Min Range: -7.3441
Max Act: 7.3441. Min Act: -0.1700
Data Index: 1418904 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3441. Min Range: -7.3441
Max Act: 7.0629. Min Act: -0.1700
Data Index: 2693201 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.8441. Min Act: -0.1700
Data Index: 61797 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.7504. Min Act: -0.1700
Data Index: 2601289 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.7191. Min Act: -0.1700
Data Index: 5652489 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6879. Min Act: -0.1700
Data Index: 5664877 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6879. Min Act: -0.1700
Data Index: 7675509 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6566. Min Act: -0.1700
Data Index: 2252318 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6566. Min Act: -0.1700
Data Index: 3808873 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6254. Min Act: -0.1700
Data Index: 3791682 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6254. Min Act: -0.1700
Data Index: 8047055 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.6566. Min Act: -0.1700
Data Index: 3569670 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5629. Min Act: -0.1700
Data Index: 7954773 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5941. Min Act: -0.1700
Data Index: 2621604 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5629. Min Act: -0.1700
Data Index: 746561 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5629. Min Act: -0.1700
Data Index: 8024345 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5941. Min Act: -0.1700
Data Index: 8130961 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5316. Min Act: -0.1700
Data Index: 7803192 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3441. Min Range: -7.3441
Max Act: 6.5316. Min Act: -0.1700
Data Index: 821466 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19