Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3451. Min Range: -8.3451
Max Act: 8.3451. Min Act: -0.1700
Data Index: 8186572 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3451. Min Range: -8.3451
Max Act: 8.0326. Min Act: -0.1700
Data Index: 8649008 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.6888. Min Act: -0.1700
Data Index: 6488731 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.5951. Min Act: -0.1700
Data Index: 3706890 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.5013. Min Act: -0.1700
Data Index: 1225511 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.5013. Min Act: -0.1700
Data Index: 6810396 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.5013. Min Act: -0.1700
Data Index: 2379239 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.4076. Min Act: -0.1700
Data Index: 3158478 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.3451. Min Act: -0.1700
Data Index: 131505 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.3138. Min Act: -0.1700
Data Index: 965766 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.3138. Min Act: -0.1700
Data Index: 7632380 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.3138. Min Act: -0.1700
Data Index: 8347944 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.3138. Min Act: -0.1700
Data Index: 7513138 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2513. Min Act: -0.1700
Data Index: 7029828 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2826. Min Act: -0.1700
Data Index: 3189179 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.1888. Min Act: -0.1700
Data Index: 6560504 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2201. Min Act: -0.1700
Data Index: 7917038 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2513. Min Act: -0.1700
Data Index: 919019 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2201. Min Act: -0.1700
Data Index: 6244734 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3451. Min Range: -8.3451
Max Act: 7.2201. Min Act: -0.1700
Data Index: 2275308 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19