Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.9488. Min Act: -0.1700
Data Index: 1211119 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.5738. Min Act: -0.1700
Data Index: 5423273 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.2613. Min Act: -0.1700
Data Index: 4917121 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.1988. Min Act: -0.1700
Data Index: 1738500 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.1363. Min Act: -0.1699
Data Index: 3268889 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.0738. Min Act: -0.1700
Data Index: 7129047 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 154262 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 4657149 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 511015 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9488. Min Range: -8.9488
Max Act: 8.0113. Min Act: -0.1700
Data Index: 2960330 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.9488. Min Act: -0.1700
Data Index: 7458405 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.9488. Min Act: -0.1700
Data Index: 5425252 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.9488. Min Act: -0.1700
Data Index: 6231575 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.9488. Min Act: -0.1700
Data Index: 391305 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.8863. Min Act: -0.1700
Data Index: 132433 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.8863. Min Act: -0.1700
Data Index: 7572859 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.8238. Min Act: -0.1700
Data Index: 5255728 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.7613. Min Act: -0.1700
Data Index: 2386946 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.8238. Min Act: -0.1700
Data Index: 7679613 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9488. Min Range: -8.9488
Max Act: 7.7613. Min Act: -0.1700
Data Index: 2002982 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19