Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.4388. Min Act: -0.1700
Data Index: 8281750 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.1888. Min Act: -0.1699
Data Index: 3943189 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.1888. Min Act: -0.1700
Data Index: 2545737 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.1576. Min Act: -0.1700
Data Index: 1097743 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.1576. Min Act: -0.1700
Data Index: 7602919 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0951. Min Act: -0.1700
Data Index: 6131928 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0951. Min Act: -0.1700
Data Index: 3680549 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0951. Min Act: -0.1700
Data Index: 6488239 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0326. Min Act: -0.1700
Data Index: 7935146 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0638. Min Act: -0.1700
Data Index: 6371045 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0013. Min Act: -0.1700
Data Index: 5892654 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0013. Min Act: -0.1700
Data Index: 462745 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0013. Min Act: -0.1700
Data Index: 7892315 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4388. Min Range: -5.4388
Max Act: 5.0013. Min Act: -0.1700
Data Index: 5280742 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.9076. Min Act: -0.1700
Data Index: 42665 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.9076. Min Act: -0.1700
Data Index: 733263 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.9388. Min Act: -0.1700
Data Index: 3388027 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.9076. Min Act: -0.1700
Data Index: 8477059 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.9076. Min Act: -0.1700
Data Index: 5856428 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4388. Min Range: -5.4388
Max Act: 4.8763. Min Act: -0.1700
Data Index: 6373121 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19