Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0273. Min Range: -8.0273
Max Act: 8.0273. Min Act: -0.1700
Data Index: 7548140 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.7148. Min Act: -0.1700
Data Index: 1163733 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.7148. Min Act: -0.1700
Data Index: 1674177 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.6211. Min Act: -0.1700
Data Index: 1744511 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.6211. Min Act: -0.1700
Data Index: 2874871 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.6211. Min Act: -0.1700
Data Index: 7872885 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.5586. Min Act: -0.1700
Data Index: 3301885 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.5273. Min Act: -0.1700
Data Index: 8605425 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.5586. Min Act: -0.1700
Data Index: 4215045 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4961. Min Act: -0.1700
Data Index: 889749 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4648. Min Act: -0.1700
Data Index: 4225847 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4023. Min Act: -0.1700
Data Index: 158150 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4648. Min Act: -0.1700
Data Index: 3720391 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4023. Min Act: -0.1700
Data Index: 5603757 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4023. Min Act: -0.1700
Data Index: 5604888 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4023. Min Act: -0.1700
Data Index: 3046995 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.3398. Min Act: -0.1700
Data Index: 3736089 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.4023. Min Act: -0.1700
Data Index: 8224429 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.3398. Min Act: -0.1700
Data Index: 5073126 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0273. Min Range: -8.0273
Max Act: 7.3398. Min Act: -0.1700
Data Index: 5357465 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19