Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3464. Min Range: -6.3464
Max Act: 6.3464. Min Act: -0.1700
Data Index: 7581790 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3464. Min Range: -6.3464
Max Act: 6.3464. Min Act: -0.1700
Data Index: 2118874 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3464. Min Range: -6.3464
Max Act: 6.2526. Min Act: -0.1700
Data Index: 6982437 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3464. Min Range: -6.3464
Max Act: 6.0964. Min Act: -0.1700
Data Index: 4388207 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3464. Min Range: -6.3464
Max Act: 6.0339. Min Act: -0.1700
Data Index: 601850 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.9714. Min Act: -0.1700
Data Index: 1862505 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.9401. Min Act: -0.1700
Data Index: 3819246 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.9401. Min Act: -0.1700
Data Index: 6487200 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.9089. Min Act: -0.1700
Data Index: 4175065 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.9089. Min Act: -0.1700
Data Index: 4017283 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8776. Min Act: -0.1700
Data Index: 7673621 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8776. Min Act: -0.1700
Data Index: 862266 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8776. Min Act: -0.1700
Data Index: 6641971 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8464. Min Act: -0.1700
Data Index: 3389700 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8151. Min Act: -0.1700
Data Index: 4236884 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.7839. Min Act: -0.1700
Data Index: 4153451 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.8151. Min Act: -0.1700
Data Index: 7700990 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.7839. Min Act: -0.1700
Data Index: 7836206 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.7526. Min Act: -0.1700
Data Index: 118484 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3464. Min Range: -6.3464
Max Act: 5.7839. Min Act: -0.1700
Data Index: 6012972 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19