Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.7331. Min Act: -0.1700
Data Index: 4097119 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.6081. Min Act: -0.1700
Data Index: 2213094 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.5769. Min Act: -0.1700
Data Index: 2217227 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.5769. Min Act: -0.1700
Data Index: 2007863 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.6081. Min Act: -0.1700
Data Index: 5614832 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.5456. Min Act: -0.1700
Data Index: 7312345 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.5456. Min Act: -0.1700
Data Index: 2070740 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4831. Min Act: -0.1700
Data Index: 7637864 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4831. Min Act: -0.1700
Data Index: 7720139 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4831. Min Act: -0.1700
Data Index: 3977400 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7312344 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7212442 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4519. Min Act: -0.1700
Data Index: 4824428 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4519. Min Act: -0.1700
Data Index: 6008946 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4519. Min Act: -0.1700
Data Index: 6575577 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.4206. Min Act: -0.1700
Data Index: 4670445 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.3894. Min Act: -0.1700
Data Index: 6595611 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.3894. Min Act: -0.1700
Data Index: 3635471 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5767995 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7331. Min Range: -5.7331
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5336016 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19