Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 326 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.6502. Min Act: -0.1700
Data Index: 3503010 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 586424 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.5565. Min Act: -0.1700
Data Index: 8338393 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3141564 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.5252. Min Act: -0.1700
Data Index: 2317994 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.4940. Min Act: -0.1700
Data Index: 1182302 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.4315. Min Act: -0.1700
Data Index: 2573504 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2822531 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.4315. Min Act: -0.1700
Data Index: 7283266 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.4315. Min Act: -0.1700
Data Index: 252615 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3690. Min Act: -0.1700
Data Index: 5532422 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6584105 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3377. Min Act: -0.1700
Data Index: 5940514 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6468071 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3690. Min Act: -0.1700
Data Index: 4301146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3377. Min Act: -0.1700
Data Index: 5120159 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3377. Min Act: -0.1700
Data Index: 4837625 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.2752. Min Act: -0.1700
Data Index: 8734198 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.3065. Min Act: -0.1700
Data Index: 2835804 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6502. Min Range: -5.6502
Max Act: 5.2752. Min Act: -0.1700
Data Index: 4604407 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19