Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2087. Min Range: -3.2087
Max Act: 3.2087. Min Act: -0.1700
Data Index: 1746249 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.9722. Min Act: -0.1700
Data Index: 948692 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8771. Min Act: -0.1700
Data Index: 3177830 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8930. Min Act: -0.1700
Data Index: 3464477 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8771. Min Act: -0.1700
Data Index: 5058431 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8613. Min Act: -0.1700
Data Index: 1474726 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8454. Min Act: -0.1700
Data Index: 3378592 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8613. Min Act: -0.1700
Data Index: 7042151 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8613. Min Act: -0.1700
Data Index: 5741531 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8295. Min Act: -0.1700
Data Index: 7095777 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8454. Min Act: -0.1700
Data Index: 397743 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8454. Min Act: -0.1700
Data Index: 2120258 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8136. Min Act: -0.1700
Data Index: 3303303 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8295. Min Act: -0.1700
Data Index: 562683 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8295. Min Act: -0.1700
Data Index: 1554371 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8295. Min Act: -0.1700
Data Index: 7411742 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8136. Min Act: -0.1700
Data Index: 1229116 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8136. Min Act: -0.1700
Data Index: 8176791 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8454. Min Act: -0.1700
Data Index: 4800859 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2087. Min Range: -3.2087
Max Act: 2.8136. Min Act: -0.1700
Data Index: 4002112 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19