Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.4672. Min Act: -0.1700
Data Index: 5527603 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.4047. Min Act: -0.1700
Data Index: 4919691 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.2484. Min Act: -0.1700
Data Index: 918082 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.1234. Min Act: -0.1700
Data Index: 5662221 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.1234. Min Act: -0.1700
Data Index: 5961765 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.1234. Min Act: -0.1700
Data Index: 2673454 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4672. Min Range: -7.4672
Max Act: 7.0609. Min Act: -0.1700
Data Index: 60442 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.9984. Min Act: -0.1700
Data Index: 209952 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.9672. Min Act: -0.1700
Data Index: 2562528 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.9047. Min Act: -0.1700
Data Index: 4946207 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.9047. Min Act: -0.1700
Data Index: 407925 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.8422. Min Act: -0.1700
Data Index: 745612 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7797. Min Act: -0.1700
Data Index: 6210437 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7797. Min Act: -0.1700
Data Index: 2664640 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7484. Min Act: -0.1700
Data Index: 8696252 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7797. Min Act: -0.1700
Data Index: 5908648 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.6859. Min Act: -0.1700
Data Index: 1064660 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7172. Min Act: -0.1700
Data Index: 5058596 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.7172. Min Act: -0.1700
Data Index: 8521436 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4672. Min Range: -7.4672
Max Act: 6.6859. Min Act: -0.1700
Data Index: 5247990 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19