Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4434 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1291. Min Range: -6.1291
Max Act: 6.1291. Min Act: -0.1700
Data Index: 8174043 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1291. Min Range: -6.1291
Max Act: 6.0041. Min Act: -0.1700
Data Index: 3865985 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1291. Min Range: -6.1291
Max Act: 6.0041. Min Act: -0.1700
Data Index: 4123331 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.9729. Min Act: -0.1700
Data Index: 3471815 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8791. Min Act: -0.1700
Data Index: 4600461 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8791. Min Act: -0.1700
Data Index: 1540170 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8791. Min Act: -0.1700
Data Index: 5284647 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6657199 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8479. Min Act: -0.1700
Data Index: 4806879 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8166. Min Act: -0.1700
Data Index: 2666294 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8166. Min Act: -0.1700
Data Index: 82762 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7854. Min Act: -0.1700
Data Index: 6939974 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.8166. Min Act: -0.1700
Data Index: 7757463 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7854. Min Act: -0.1700
Data Index: 5542292 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7541. Min Act: -0.1700
Data Index: 1892865 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7541. Min Act: -0.1700
Data Index: 2616206 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7854. Min Act: -0.1700
Data Index: 5998446 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7854. Min Act: -0.1700
Data Index: 8126032 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7854. Min Act: -0.1700
Data Index: 5960770 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1291. Min Range: -6.1291
Max Act: 5.7541. Min Act: -0.1700
Data Index: 2053010 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19