Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.7552. Min Range: -13.7552
Max Act: 13.7552. Min Act: -0.1700
Data Index: 5861040 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.7552. Min Range: -13.7552
Max Act: 13.4427. Min Act: -0.1700
Data Index: 2700626 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.7552. Min Range: -13.7552
Max Act: 13.0677. Min Act: -0.1700
Data Index: 7889840 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.6302. Min Act: -0.1700
Data Index: 3789230 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.6302. Min Act: -0.1700
Data Index: 7629619 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.6302. Min Act: -0.1700
Data Index: 8450381 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.6302. Min Act: -0.1700
Data Index: 6761308 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.5677. Min Act: -0.1700
Data Index: 4116816 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.5052. Min Act: -0.1700
Data Index: 5980132 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.5052. Min Act: -0.1700
Data Index: 7119909 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.4427. Min Act: -0.1700
Data Index: 4708540 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.4427. Min Act: -0.1526
Data Index: 6214491 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.5052. Min Act: -0.1700
Data Index: 7486242 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.3802. Min Act: -0.1700
Data Index: 2587424 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.3177. Min Act: -0.1700
Data Index: 6254675 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.3177. Min Act: -0.1700
Data Index: 3024969 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.2552. Min Act: -0.1700
Data Index: 3887917 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.1927. Min Act: -0.1700
Data Index: 2957931 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.1302. Min Act: -0.1700
Data Index: 2873586 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.7552. Min Range: -13.7552
Max Act: 12.1927. Min Act: -0.1700
Data Index: 2295498 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19