Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.7690. Min Act: -0.1700
Data Index: 6233347 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.6440. Min Act: -0.1700
Data Index: 4065053 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.5815. Min Act: -0.1700
Data Index: 5014850 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.6127. Min Act: -0.1700
Data Index: 3283811 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.5502. Min Act: -0.1700
Data Index: 332736 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.5502. Min Act: -0.1700
Data Index: 7849858 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.5502. Min Act: -0.1700
Data Index: 4151504 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.4877. Min Act: -0.1700
Data Index: 866007 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.4877. Min Act: -0.1700
Data Index: 8458365 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.4565. Min Act: -0.1700
Data Index: 5042887 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.4565. Min Act: -0.1700
Data Index: 5014860 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3627. Min Act: -0.1700
Data Index: 8628442 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3940. Min Act: -0.1700
Data Index: 406769 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3940. Min Act: -0.1700
Data Index: 4590173 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3627. Min Act: -0.1700
Data Index: 652362 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3940. Min Act: -0.1700
Data Index: 5649212 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3627. Min Act: -0.1700
Data Index: 6188075 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3315. Min Act: -0.1700
Data Index: 710645 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3315. Min Act: -0.1700
Data Index: 3753523 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7690. Min Range: -4.7690
Max Act: 4.3315. Min Act: -0.1700
Data Index: 1708243 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19