Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.6112. Min Act: -0.1700
Data Index: 570881 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.4862. Min Act: -0.1700
Data Index: 8068708 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.2987. Min Act: -0.1700
Data Index: 4436973 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.2987. Min Act: -0.1700
Data Index: 7951295 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.2362. Min Act: -0.1700
Data Index: 4983513 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.2362. Min Act: -0.1700
Data Index: 6636976 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.1737. Min Act: -0.1700
Data Index: 2093589 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.2362. Min Act: -0.1700
Data Index: 3549082 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.1112. Min Act: -0.1700
Data Index: 6451209 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.1112. Min Act: -0.1700
Data Index: 6565432 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.1112. Min Act: -0.1700
Data Index: 7055936 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.0487. Min Act: -0.1700
Data Index: 3786214 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.0487. Min Act: -0.1700
Data Index: 4778538 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.0487. Min Act: -0.1700
Data Index: 1145673 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.0487. Min Act: -0.1700
Data Index: 7573791 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6112. Min Range: -9.6112
Max Act: 8.9862. Min Act: -0.1700
Data Index: 8808426 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6112. Min Range: -9.6112
Max Act: 8.9862. Min Act: -0.1699
Data Index: 4813193 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6112. Min Range: -9.6112
Max Act: 9.0487. Min Act: -0.1700
Data Index: 4791188 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6112. Min Range: -9.6112
Max Act: 8.9862. Min Act: -0.1700
Data Index: 1250945 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6112. Min Range: -9.6112
Max Act: 8.9862. Min Act: -0.1700
Data Index: 1026424 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19