Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1993. Min Range: -7.1993
Max Act: 7.1993. Min Act: -0.1700
Data Index: 5775060 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1993. Min Range: -7.1993
Max Act: 7.1056. Min Act: -0.1700
Data Index: 348733 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.9806. Min Act: -0.1700
Data Index: 428725 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.8868. Min Act: -0.1700
Data Index: 941011 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.8243. Min Act: -0.1700
Data Index: 5743309 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.8243. Min Act: -0.1700
Data Index: 1088712 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.7931. Min Act: -0.1700
Data Index: 769540 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.7618. Min Act: -0.1700
Data Index: 4788759 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.7931. Min Act: -0.1700
Data Index: 8019614 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.7306. Min Act: -0.1700
Data Index: 6581283 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.6368. Min Act: -0.1700
Data Index: 7625744 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.6056. Min Act: -0.1700
Data Index: 5701824 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.5431. Min Act: -0.1700
Data Index: 3513045 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.5118. Min Act: -0.1700
Data Index: 8270168 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2310096 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.4806. Min Act: -0.1700
Data Index: 3915585 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.4493. Min Act: -0.1700
Data Index: 1276780 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.4181. Min Act: -0.1700
Data Index: 8149426 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.4493. Min Act: -0.1700
Data Index: 4854415 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1993. Min Range: -7.1993
Max Act: 6.4493. Min Act: -0.1700
Data Index: 956223 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19