Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3016. Min Range: -6.3016
Max Act: 6.3016. Min Act: -0.1700
Data Index: 3375390 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.6766. Min Act: -0.1700
Data Index: 7281454 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.5828. Min Act: -0.1700
Data Index: 8772054 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.4578. Min Act: -0.1700
Data Index: 4607615 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.4266. Min Act: -0.1699
Data Index: 7638388 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.4578. Min Act: -0.1700
Data Index: 3194131 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.4266. Min Act: -0.1695
Data Index: 954021 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 8622692 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 433048 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 1087389 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.3328. Min Act: -0.1700
Data Index: 2445540 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.3328. Min Act: -0.1700
Data Index: 4791870 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.2703. Min Act: -0.1700
Data Index: 1886806 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.2703. Min Act: -0.1700
Data Index: 4791868 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.1766. Min Act: -0.1700
Data Index: 6769595 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.2078. Min Act: -0.1700
Data Index: 3231319 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.1766. Min Act: -0.1700
Data Index: 5637329 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.1766. Min Act: -0.1700
Data Index: 2679933 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.1766. Min Act: -0.1700
Data Index: 1128848 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3016. Min Range: -6.3016
Max Act: 5.1453. Min Act: -0.1700
Data Index: 7727896 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19