Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.8618. Min Act: -0.1700
Data Index: 5279507 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.8305. Min Act: -0.1700
Data Index: 5279506 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.7993. Min Act: -0.1700
Data Index: 5488777 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.7993. Min Act: -0.1700
Data Index: 2975652 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.7368. Min Act: -0.1700
Data Index: 2093579 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.7680. Min Act: -0.1700
Data Index: 5539512 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6118. Min Act: -0.1700
Data Index: 4725655 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6743. Min Act: -0.1700
Data Index: 7161491 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6118. Min Act: -0.1700
Data Index: 5731506 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6118. Min Act: -0.1700
Data Index: 3784555 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6118. Min Act: -0.1700
Data Index: 487181 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5805. Min Act: -0.1700
Data Index: 3385768 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.6118. Min Act: -0.1700
Data Index: 4530989 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5805. Min Act: -0.1700
Data Index: 98013 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5493. Min Act: -0.1700
Data Index: 5772154 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5493. Min Act: -0.1700
Data Index: 4087686 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5180. Min Act: -0.1700
Data Index: 3100765 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5493. Min Act: -0.1700
Data Index: 7371535 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.5493. Min Act: -0.1700
Data Index: 7538234 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8618. Min Range: -7.8618
Max Act: 7.4868. Min Act: -0.1700
Data Index: 2058862 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19