Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.9022. Min Act: -0.1700
Data Index: 4245548 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.8709. Min Act: -0.1700
Data Index: 4905665 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.7772. Min Act: -0.1700
Data Index: 5147002 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4647. Min Act: -0.1700
Data Index: 6822211 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4647. Min Act: -0.1700
Data Index: 4635631 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.4334. Min Act: -0.1700
Data Index: 7653739 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.3397. Min Act: -0.1700
Data Index: 378895 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.2459. Min Act: -0.1700
Data Index: 7717259 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.1834. Min Act: -0.1700
Data Index: 5278953 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.1522. Min Act: -0.1700
Data Index: 1139093 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.1522. Min Act: -0.1700
Data Index: 4431834 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.1209. Min Act: -0.1700
Data Index: 6808337 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.1522. Min Act: -0.1700
Data Index: 7215703 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.0584. Min Act: -0.1700
Data Index: 7134625 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6722065 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.0272. Min Act: -0.1700
Data Index: 6045022 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.0272. Min Act: -0.1700
Data Index: 6802607 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9022. Min Range: -6.9022
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6571835 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9022. Min Range: -6.9022
Max Act: 5.9959. Min Act: -0.1700
Data Index: 6756588 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9022. Min Range: -6.9022
Max Act: 5.9647. Min Act: -0.1700
Data Index: 2727090 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19