Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.7155. Min Act: -0.1700
Data Index: 6581783 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.6842. Min Act: -0.1700
Data Index: 2838493 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.6842. Min Act: -0.1700
Data Index: 2838482 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5481624 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.6217. Min Act: -0.1700
Data Index: 2059756 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.6530. Min Act: -0.1700
Data Index: 6802665 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5905. Min Act: -0.1700
Data Index: 6277434 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5905. Min Act: -0.1700
Data Index: 993698 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.6217. Min Act: -0.1700
Data Index: 4629866 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5217427 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5280. Min Act: -0.1700
Data Index: 8051105 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5592. Min Act: -0.1700
Data Index: 1682166 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5280. Min Act: -0.1700
Data Index: 5036291 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5592. Min Act: -0.1700
Data Index: 7978983 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5280. Min Act: -0.1700
Data Index: 7966594 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5280. Min Act: -0.1700
Data Index: 7728029 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.4967. Min Act: -0.1700
Data Index: 7155848 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5280. Min Act: -0.1700
Data Index: 3798874 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5592. Min Act: -0.1700
Data Index: 2739867 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7155. Min Range: -4.7155
Max Act: 4.5592. Min Act: -0.1700
Data Index: 325615 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19