Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.5231. Min Act: -0.1700
Data Index: 3129268 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.5231. Min Act: -0.1700
Data Index: 6450250 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.4606. Min Act: -0.1700
Data Index: 8023371 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.4294. Min Act: -0.1700
Data Index: 5630994 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.3356. Min Act: -0.1700
Data Index: 6119454 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 5774542 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 5840172 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 7782888 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 1641897 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 5130506 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.2419. Min Act: -0.1700
Data Index: 3640778 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1794. Min Act: -0.1700
Data Index: 4432028 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1794. Min Act: -0.1700
Data Index: 2658427 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1481. Min Act: -0.1700
Data Index: 5405121 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1794. Min Act: -0.1700
Data Index: 2722792 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.0856. Min Act: -0.1700
Data Index: 188760 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1169. Min Act: -0.1700
Data Index: 3045803 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.0856. Min Act: -0.1700
Data Index: 4531962 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1169. Min Act: -0.1700
Data Index: 134052 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5231. Min Range: -7.5231
Max Act: 7.1169. Min Act: -0.1700
Data Index: 4789120 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19