Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4096 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1854. Min Range: -8.1854
Max Act: 8.1854. Min Act: -0.1700
Data Index: 6090525 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.8416. Min Act: -0.1700
Data Index: 3300438 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.6854. Min Act: -0.1700
Data Index: 7376632 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4979. Min Act: -0.1700
Data Index: 2880249 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.5291. Min Act: -0.1700
Data Index: 1460605 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4979. Min Act: -0.1700
Data Index: 7925709 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4979. Min Act: -0.1700
Data Index: 469238 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4666. Min Act: -0.1700
Data Index: 1770672 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4354. Min Act: -0.1700
Data Index: 992255 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4354. Min Act: -0.1700
Data Index: 7871489 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4354. Min Act: -0.1700
Data Index: 4016559 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4041. Min Act: -0.1700
Data Index: 8207378 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.4041. Min Act: -0.1700
Data Index: 4696385 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.3416. Min Act: -0.1700
Data Index: 1948882 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.3416. Min Act: -0.1700
Data Index: 253609 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.3104. Min Act: -0.1700
Data Index: 5919217 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.3104. Min Act: -0.1700
Data Index: 2714330 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.2166. Min Act: -0.1700
Data Index: 3335153 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.2166. Min Act: -0.1700
Data Index: 8367067 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1854. Min Range: -8.1854
Max Act: 7.1854. Min Act: -0.1700
Data Index: 7622586 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19