Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 626 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0779. Min Range: -9.0779
Max Act: 9.0779. Min Act: -0.1700
Data Index: 2161330 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0779. Min Range: -9.0779
Max Act: 9.0779. Min Act: -0.1700
Data Index: 2200566 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0779. Min Range: -9.0779
Max Act: 9.0779. Min Act: -0.1700
Data Index: 322450 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0779. Min Range: -9.0779
Max Act: 9.0154. Min Act: -0.1700
Data Index: 4184162 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.9529. Min Act: -0.1700
Data Index: 3897327 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.8904. Min Act: -0.1700
Data Index: 6186584 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.8904. Min Act: -0.1700
Data Index: 3377911 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.7654. Min Act: -0.1700
Data Index: 3522094 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.7654. Min Act: -0.1700
Data Index: 4184161 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.7029. Min Act: -0.1700
Data Index: 2478410 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.7029. Min Act: -0.1700
Data Index: 1258084 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5779. Min Act: -0.1700
Data Index: 5492672 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5779. Min Act: -0.1700
Data Index: 5177173 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5779. Min Act: -0.1700
Data Index: 8607727 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5154. Min Act: -0.1700
Data Index: 2538478 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5154. Min Act: -0.1700
Data Index: 793879 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5154. Min Act: -0.1700
Data Index: 3572347 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5154. Min Act: -0.1700
Data Index: 4110716 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5779. Min Act: -0.1700
Data Index: 3117016 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0779. Min Range: -9.0779
Max Act: 8.5154. Min Act: -0.1700
Data Index: 2148288 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19