Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.2388. Min Act: -0.1700
Data Index: 5838734 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.2076. Min Act: -0.1700
Data Index: 3622889 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.1763. Min Act: -0.1700
Data Index: 136904 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1747114 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.0826. Min Act: -0.1700
Data Index: 4159815 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2388. Min Range: -6.2388
Max Act: 6.0513. Min Act: -0.1700
Data Index: 6525078 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.9888. Min Act: -0.1700
Data Index: 1601342 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1414267 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6039197 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4381218 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8638. Min Act: -0.1700
Data Index: 2241219 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8638. Min Act: -0.1700
Data Index: 6482326 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8013. Min Act: -0.1700
Data Index: 2786850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.7701. Min Act: -0.1700
Data Index: 2355395 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8013. Min Act: -0.1700
Data Index: 4446656 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8326. Min Act: -0.1700
Data Index: 1985657 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.8013. Min Act: -0.1700
Data Index: 7754176 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.7701. Min Act: -0.1700
Data Index: 1640022 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.7701. Min Act: -0.1700
Data Index: 2485970 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2388. Min Range: -6.2388
Max Act: 5.7701. Min Act: -0.1700
Data Index: 4002528 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19