Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.7425. Min Act: -0.1700
Data Index: 2835295 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.6488. Min Act: -0.1700
Data Index: 2811242 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.5863. Min Act: -0.1700
Data Index: 7481953 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.5550. Min Act: -0.1700
Data Index: 5462483 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.4613. Min Act: -0.1700
Data Index: 1109055 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.4613. Min Act: -0.1700
Data Index: 3824321 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.3988. Min Act: -0.1700
Data Index: 6618620 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.4300. Min Act: -0.1700
Data Index: 401051 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.3363. Min Act: -0.1700
Data Index: 1380717 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.3050. Min Act: -0.1700
Data Index: 7784978 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.3050. Min Act: -0.1700
Data Index: 8590914 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.2738. Min Act: -0.1700
Data Index: 5225792 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.2738. Min Act: -0.1700
Data Index: 469367 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.2738. Min Act: -0.1700
Data Index: 6058643 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.2113. Min Act: -0.1700
Data Index: 401052 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.1800. Min Act: -0.1700
Data Index: 2082806 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.1800. Min Act: -0.1700
Data Index: 6636044 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.1488. Min Act: -0.1700
Data Index: 6432258 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.1175. Min Act: -0.1700
Data Index: 5925524 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7425. Min Range: -6.7425
Max Act: 6.1175. Min Act: -0.1700
Data Index: 5407557 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19