Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0670. Min Range: -6.0670
Max Act: 6.0670. Min Act: -0.1700
Data Index: 144537 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.7858. Min Act: -0.1700
Data Index: 1876898 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.7233. Min Act: -0.1700
Data Index: 1492555 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.6295. Min Act: -0.1700
Data Index: 6818311 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5670. Min Act: -0.1700
Data Index: 2001244 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5670. Min Act: -0.1700
Data Index: 3529327 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5358. Min Act: -0.1700
Data Index: 8557124 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5358. Min Act: -0.1700
Data Index: 1312512 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7566553 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.5358. Min Act: -0.1700
Data Index: 4038527 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4733. Min Act: -0.1700
Data Index: 6308282 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4733. Min Act: -0.1700
Data Index: 2796715 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4733. Min Act: -0.1700
Data Index: 7005765 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4733. Min Act: -0.1700
Data Index: 980491 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4108. Min Act: -0.1700
Data Index: 5342256 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4420. Min Act: -0.1700
Data Index: 7221898 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4420. Min Act: -0.1700
Data Index: 5146911 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4420. Min Act: -0.1700
Data Index: 4976176 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4420. Min Act: -0.1700
Data Index: 4847577 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.4420. Min Act: -0.1700
Data Index: 2796717 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19