Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.9166. Min Act: -0.1700
Data Index: 2488086 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.8541. Min Act: -0.1698
Data Index: 803928 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.7604. Min Act: -0.1700
Data Index: 4844986 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.7604. Min Act: -0.1700
Data Index: 3622221 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6666. Min Act: -0.1700
Data Index: 3992399 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6979. Min Act: -0.1700
Data Index: 1593515 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6666. Min Act: -0.1700
Data Index: 7622252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6666. Min Act: -0.1700
Data Index: 8549510 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6666. Min Act: -0.1700
Data Index: 3368951 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6666. Min Act: -0.1700
Data Index: 3622218 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6354. Min Act: -0.1700
Data Index: 4289601 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6041. Min Act: -0.1700
Data Index: 5738962 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6041. Min Act: -0.1700
Data Index: 8346359 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6041. Min Act: -0.1700
Data Index: 7666485 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.5729. Min Act: -0.1700
Data Index: 7922346 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.5729. Min Act: -0.1700
Data Index: 3784172 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.6041. Min Act: -0.1700
Data Index: 1786731 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.5729. Min Act: -0.1700
Data Index: 4397129 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.5729. Min Act: -0.1700
Data Index: 3519300 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9166. Min Range: -4.9166
Max Act: 4.5729. Min Act: -0.1700
Data Index: 861348 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19