Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3669. Min Range: -6.3669
Max Act: 6.3669. Min Act: -0.1700
Data Index: 8025185 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3669. Min Range: -6.3669
Max Act: 6.0231. Min Act: -0.1700
Data Index: 8025186 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.8981. Min Act: -0.1700
Data Index: 1612306 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.7419. Min Act: -0.1700
Data Index: 15422 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.7106. Min Act: -0.1700
Data Index: 4170014 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6169. Min Act: -0.1700
Data Index: 1266738 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 5037622 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 1017482 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6169. Min Act: -0.1700
Data Index: 5716674 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 7471668 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 5831590 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.6481. Min Act: -0.1700
Data Index: 8394900 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5856. Min Act: -0.1700
Data Index: 8781849 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5544. Min Act: -0.1700
Data Index: 8571774 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5544. Min Act: -0.1700
Data Index: 2608419 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5544. Min Act: -0.1700
Data Index: 2608422 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5231. Min Act: -0.1700
Data Index: 1612779 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.4919. Min Act: -0.1700
Data Index: 5482973 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5231. Min Act: -0.1700
Data Index: 5146793 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3669. Min Range: -6.3669
Max Act: 5.5544. Min Act: -0.1700
Data Index: 4951124 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19