Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.8977. Min Act: -0.1700
Data Index: 382283 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.6790. Min Act: -0.1700
Data Index: 1334631 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.5852. Min Act: -0.1700
Data Index: 6976540 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.5227. Min Act: -0.1700
Data Index: 7040437 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.4915. Min Act: -0.1700
Data Index: 7090794 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.4602. Min Act: -0.1700
Data Index: 3266660 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.4602. Min Act: -0.1700
Data Index: 374725 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3977. Min Act: -0.1700
Data Index: 3586844 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3977. Min Act: -0.1700
Data Index: 6659808 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3665. Min Act: -0.1700
Data Index: 3980924 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3352. Min Act: -0.1700
Data Index: 3374329 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3352. Min Act: -0.1700
Data Index: 4493771 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3040. Min Act: -0.1700
Data Index: 3292575 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.3040. Min Act: -0.1700
Data Index: 1613358 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2727. Min Act: -0.1700
Data Index: 7787032 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2414. Min Act: -0.1700
Data Index: 2966728 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2102. Min Act: -0.1700
Data Index: 5928148 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2414. Min Act: -0.1700
Data Index: 5082537 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2414. Min Act: -0.1700
Data Index: 7217405 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8977. Min Range: -4.8977
Max Act: 4.2102. Min Act: -0.1700
Data Index: 4245300 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19