Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.8132. Min Act: -0.1700
Data Index: 4481401 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.8444. Min Act: -0.1700
Data Index: 1533692 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.6257. Min Act: -0.1700
Data Index: 4706690 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5944. Min Act: -0.1700
Data Index: 6813783 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5632. Min Act: -0.1700
Data Index: 2152542 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5632. Min Act: -0.1700
Data Index: 8729232 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5319. Min Act: -0.1700
Data Index: 6268069 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5319. Min Act: -0.1700
Data Index: 1474293 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5319. Min Act: -0.1700
Data Index: 302803 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5319. Min Act: -0.1700
Data Index: 1338245 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5007. Min Act: -0.1700
Data Index: 1837431 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5632. Min Act: -0.1700
Data Index: 4900610 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5007. Min Act: -0.1700
Data Index: 8639870 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.5007. Min Act: -0.1700
Data Index: 532167 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4694. Min Act: -0.1700
Data Index: 6268072 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4694. Min Act: -0.1700
Data Index: 7434806 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4694. Min Act: -0.1700
Data Index: 6767017 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4382. Min Act: -0.1700
Data Index: 1343861 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4382. Min Act: -0.1700
Data Index: 3379732 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8444. Min Range: -6.8444
Max Act: 6.4382. Min Act: -0.1700
Data Index: 8494555 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19