Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.7234. Min Act: -0.1700
Data Index: 8290570 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 5405146 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.6609. Min Act: -0.1700
Data Index: 8215593 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.5984. Min Act: -0.1700
Data Index: 2829886 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.4734. Min Act: -0.1700
Data Index: 3048137 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.5359. Min Act: -0.1700
Data Index: 5271483 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.5984. Min Act: -0.1700
Data Index: 4625453 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.5359. Min Act: -0.1700
Data Index: 7576925 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.5359. Min Act: -0.1700
Data Index: 196582 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.4422. Min Act: -0.1700
Data Index: 7591213 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.3797. Min Act: -0.1700
Data Index: 4002173 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.3484. Min Act: -0.1699
Data Index: 377379 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.3172. Min Act: -0.1700
Data Index: 5606993 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.3172. Min Act: -0.1700
Data Index: 7837585 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.3172. Min Act: -0.1700
Data Index: 7994819 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.2547. Min Act: -0.1700
Data Index: 3588688 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.2547. Min Act: -0.1700
Data Index: 4345452 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.2547. Min Act: -0.1700
Data Index: 6293493 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.2859. Min Act: -0.1700
Data Index: 4035514 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7234. Min Range: -7.7234
Max Act: 7.2234. Min Act: -0.1700
Data Index: 200148 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19