Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.8997. Min Act: -0.1700
Data Index: 1803150 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.6497. Min Act: -0.1700
Data Index: 95350 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.6184. Min Act: -0.1700
Data Index: 928412 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.5247. Min Act: -0.1700
Data Index: 5846810 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.4309. Min Act: -0.1700
Data Index: 8060460 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.4622. Min Act: -0.1700
Data Index: 6058181 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3997. Min Act: -0.1700
Data Index: 1715437 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3684. Min Act: -0.1700
Data Index: 4673795 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3372. Min Act: -0.1700
Data Index: 5015346 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3372. Min Act: -0.1700
Data Index: 6279852 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3372. Min Act: -0.1700
Data Index: 4898570 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.3059. Min Act: -0.1700
Data Index: 3256009 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.2434. Min Act: -0.1700
Data Index: 6156583 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.2747. Min Act: -0.1700
Data Index: 4252134 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.2747. Min Act: -0.1700
Data Index: 6681922 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.2122. Min Act: -0.1700
Data Index: 2221912 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.1809. Min Act: -0.1700
Data Index: 8617598 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.1809. Min Act: -0.1700
Data Index: 5034553 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.1809. Min Act: -0.1700
Data Index: 5483036 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8997. Min Range: -7.8997
Max Act: 7.1809. Min Act: -0.1700
Data Index: 8682100 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19