Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5631 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3126. Min Range: -8.3126
Max Act: 8.3126. Min Act: -0.1700
Data Index: 7636308 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3126. Min Range: -8.3126
Max Act: 8.0626. Min Act: -0.1700
Data Index: 4086001 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8751. Min Act: -0.1700
Data Index: 6114444 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8751. Min Act: -0.1700
Data Index: 2329163 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8751. Min Act: -0.1700
Data Index: 317897 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8126. Min Act: -0.1700
Data Index: 7739686 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8126. Min Act: -0.1700
Data Index: 6644045 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8126. Min Act: -0.1700
Data Index: 6600561 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8751. Min Act: -0.1700
Data Index: 3438544 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.8126. Min Act: -0.1700
Data Index: 1430294 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.7501. Min Act: -0.1700
Data Index: 5299697 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.7813. Min Act: -0.1700
Data Index: 1609160 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.7813. Min Act: -0.1700
Data Index: 7634515 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.7188. Min Act: -0.1700
Data Index: 6844097 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.7188. Min Act: -0.1700
Data Index: 2404706 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.6876. Min Act: -0.1700
Data Index: 904720 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.6876. Min Act: -0.1700
Data Index: 4762679 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.6876. Min Act: -0.1700
Data Index: 5331592 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.6563. Min Act: -0.1700
Data Index: 6809299 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3126. Min Range: -8.3126
Max Act: 7.6563. Min Act: -0.1700
Data Index: 2127518 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19