Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7456. Min Range: -8.7456
Max Act: 8.7456. Min Act: -0.1700
Data Index: 1190741 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7456. Min Range: -8.7456
Max Act: 8.4956. Min Act: -0.1700
Data Index: 8262576 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.9644. Min Act: -0.1700
Data Index: 4328168 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.9331. Min Act: -0.1700
Data Index: 2887401 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.8081. Min Act: -0.1700
Data Index: 8820339 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.8081. Min Act: -0.1700
Data Index: 951106 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.7456. Min Act: -0.1700
Data Index: 4337431 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.7456. Min Act: -0.1700
Data Index: 1646767 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6831. Min Act: -0.1700
Data Index: 8324686 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6831. Min Act: -0.1700
Data Index: 1972022 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6831. Min Act: -0.1700
Data Index: 7064407 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.7144. Min Act: -0.1700
Data Index: 5585977 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6831. Min Act: -0.1700
Data Index: 3649406 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6519. Min Act: -0.1700
Data Index: 44010 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6831. Min Act: -0.1700
Data Index: 8056061 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.5894. Min Act: -0.1700
Data Index: 2553700 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.6206. Min Act: -0.1700
Data Index: 1230593 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.5581. Min Act: -0.1700
Data Index: 3562391 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.4956. Min Act: -0.1700
Data Index: 7574431 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7456. Min Range: -8.7456
Max Act: 7.4644. Min Act: -0.1700
Data Index: 6998478 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19