Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.9678. Min Act: -0.1700
Data Index: 8450595 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.8428. Min Act: -0.1700
Data Index: 765457 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.6241. Min Act: -0.1700
Data Index: 5660491 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.6553. Min Act: -0.1700
Data Index: 3795503 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.6553. Min Act: -0.1700
Data Index: 2328630 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.5928. Min Act: -0.1700
Data Index: 7933857 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4678. Min Act: -0.1700
Data Index: 2268992 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4991. Min Act: -0.1700
Data Index: 6719640 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 1185846 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 7176226 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 7995338 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 6055910 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 8793018 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 2527928 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4366. Min Act: -0.1700
Data Index: 1940068 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4053. Min Act: -0.1700
Data Index: 3643832 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4053. Min Act: -0.1700
Data Index: 6341736 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4053. Min Act: -0.1700
Data Index: 8130920 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.4053. Min Act: -0.1700
Data Index: 529471 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9678. Min Range: -6.9678
Max Act: 6.3741. Min Act: -0.1700
Data Index: 3088298 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19