Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.9393. Min Act: -0.1700
Data Index: 7603084 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.8768. Min Act: -0.1700
Data Index: 7655066 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.8456. Min Act: -0.1700
Data Index: 5791483 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.7831. Min Act: -0.1700
Data Index: 2936849 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.7518. Min Act: -0.1700
Data Index: 2867469 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.7518. Min Act: -0.1700
Data Index: 6913569 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6893. Min Act: -0.1700
Data Index: 7313104 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6581. Min Act: -0.1700
Data Index: 1357394 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6581. Min Act: -0.1700
Data Index: 6896149 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6268. Min Act: -0.1700
Data Index: 336525 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6268. Min Act: -0.1700
Data Index: 3552104 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5956. Min Act: -0.1700
Data Index: 2155215 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.6268. Min Act: -0.1700
Data Index: 8621741 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5956. Min Act: -0.1700
Data Index: 8621512 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5643. Min Act: -0.1700
Data Index: 4219887 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5643. Min Act: -0.1700
Data Index: 1268341 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5331. Min Act: -0.1700
Data Index: 8369172 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5018. Min Act: -0.1700
Data Index: 7823112 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5018. Min Act: -0.1700
Data Index: 2259325 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9393. Min Range: -4.9393
Max Act: 4.5331. Min Act: -0.1700
Data Index: 4566493 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19