Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3692. Min Act: -0.1700
Data Index: 6959013 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3067. Min Act: -0.1700
Data Index: 6262321 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3067. Min Act: -0.1700
Data Index: 2203741 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.2754. Min Act: -0.1700
Data Index: 8765591 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.2754. Min Act: -0.1700
Data Index: 6100847 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.2129. Min Act: -0.1700
Data Index: 2210397 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1817. Min Act: -0.1700
Data Index: 6156442 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 8797107 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 3906347 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1192. Min Act: -0.1700
Data Index: 8369820 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1192. Min Act: -0.1700
Data Index: 6617771 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0879. Min Act: -0.1700
Data Index: 8772256 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0879. Min Act: -0.1700
Data Index: 7294242 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 2363219 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0879. Min Act: -0.1700
Data Index: 8623599 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0254. Min Act: -0.1700
Data Index: 3118773 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0254. Min Act: -0.1700
Data Index: 4682599 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 334944 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 2560005 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 45382 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19