Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2445 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2243. Min Range: -8.2243
Max Act: 8.2243. Min Act: -0.1700
Data Index: 4421494 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2243. Min Range: -8.2243
Max Act: 8.0056. Min Act: -0.1700
Data Index: 4579247 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.9118. Min Act: -0.1700
Data Index: 3383267 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.9118. Min Act: -0.1700
Data Index: 8260282 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.9118. Min Act: -0.1700
Data Index: 8215320 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.8806. Min Act: -0.1700
Data Index: 4396253 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.8806. Min Act: -0.1700
Data Index: 3287016 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.8181. Min Act: -0.1700
Data Index: 3558861 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7868. Min Act: -0.1700
Data Index: 6405425 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7868. Min Act: -0.1700
Data Index: 1167902 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7868. Min Act: -0.1700
Data Index: 1811768 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7868. Min Act: -0.1700
Data Index: 5514099 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7556. Min Act: -0.1700
Data Index: 500399 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7556. Min Act: -0.1700
Data Index: 2892012 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7556. Min Act: -0.1700
Data Index: 5260179 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7243. Min Act: -0.1700
Data Index: 8096710 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.6931. Min Act: -0.1700
Data Index: 8368415 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.6618. Min Act: -0.1700
Data Index: 366236 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.7243. Min Act: -0.1700
Data Index: 6839024 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2243. Min Range: -8.2243
Max Act: 7.5993. Min Act: -0.1700
Data Index: 1811770 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19