Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0734. Min Range: -6.0734
Max Act: 6.0734. Min Act: -0.1700
Data Index: 7623799 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0734. Min Range: -6.0734
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7188045 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.9484. Min Act: -0.1700
Data Index: 929225 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.9172. Min Act: -0.1700
Data Index: 4430519 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.8859. Min Act: -0.1700
Data Index: 6073336 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.8859. Min Act: -0.1700
Data Index: 2978814 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.8547. Min Act: -0.1700
Data Index: 3803679 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.8234. Min Act: -0.1700
Data Index: 3254052 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7922. Min Act: -0.1700
Data Index: 8572390 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7609. Min Act: -0.1700
Data Index: 5848453 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7609. Min Act: -0.1700
Data Index: 1771429 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7609. Min Act: -0.1700
Data Index: 8768826 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7297. Min Act: -0.1700
Data Index: 5344582 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6521386 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7297. Min Act: -0.1700
Data Index: 5576736 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.6984. Min Act: -0.1700
Data Index: 2896244 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7297. Min Act: -0.1700
Data Index: 7240835 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.6984. Min Act: -0.1700
Data Index: 235810 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7297. Min Act: -0.1700
Data Index: 5503399 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0734. Min Range: -6.0734
Max Act: 5.7297. Min Act: -0.1700
Data Index: 1327172 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19