Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5646600 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.6390. Min Act: -0.1700
Data Index: 6621056 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.5453. Min Act: -0.1700
Data Index: 7180325 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.5453. Min Act: -0.1700
Data Index: 2912577 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.5140. Min Act: -0.1700
Data Index: 7853170 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4828. Min Act: -0.1700
Data Index: 4680337 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4828. Min Act: -0.1700
Data Index: 5170182 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4828. Min Act: -0.1700
Data Index: 2799238 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4828. Min Act: -0.1700
Data Index: 7184534 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4515. Min Act: -0.1700
Data Index: 8495808 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4515. Min Act: -0.1699
Data Index: 3253975 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4515. Min Act: -0.1700
Data Index: 2765497 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 6658291 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 5541918 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 3776197 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 286202 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 6874429 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 956912 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.4203. Min Act: -0.1700
Data Index: 6832406 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7015. Min Range: -4.7015
Max Act: 4.3890. Min Act: -0.1700
Data Index: 5751928 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19