Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1724 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.5769. Min Act: -0.1700
Data Index: 7643565 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.4519. Min Act: -0.1700
Data Index: 4361960 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.3269. Min Act: -0.1700
Data Index: 4361952 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.4519. Min Act: -0.1700
Data Index: 4361955 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.2019. Min Act: -0.1700
Data Index: 6332919 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.2019. Min Act: -0.1700
Data Index: 6839024 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.2019. Min Act: -0.1700
Data Index: 770494 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.0769. Min Act: -0.1700
Data Index: 4361953 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.5769. Min Range: -16.5769
Max Act: 16.1394. Min Act: -0.1700
Data Index: 7933189 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 2948231 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 4248605 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 7503498 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8269. Min Act: -0.1700
Data Index: 7400587 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 6839025 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 5902171 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 4217379 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8894. Min Act: -0.1700
Data Index: 4361962 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.7644. Min Act: -0.1700
Data Index: 136761 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8269. Min Act: -0.1700
Data Index: 4553723 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.5769. Min Range: -16.5769
Max Act: 15.8269. Min Act: -0.1700
Data Index: 4885748 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19