Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3850. Min Act: -0.1700
Data Index: 1071984 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3359. Min Act: -0.1700
Data Index: 1779977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3195. Min Act: -0.1700
Data Index: 1579503 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3195. Min Act: -0.1700
Data Index: 6200916 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3030. Min Act: -0.1700
Data Index: 3386415 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3030. Min Act: -0.1700
Data Index: 6093006 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3030. Min Act: -0.1700
Data Index: 2798227 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.3030. Min Act: -0.1700
Data Index: 54086 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2866. Min Act: -0.1700
Data Index: 707547 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2701. Min Act: -0.1700
Data Index: 3049925 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2701. Min Act: -0.1700
Data Index: 6078390 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2701. Min Act: -0.1700
Data Index: 2347549 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2536. Min Act: -0.1700
Data Index: 2669707 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2536. Min Act: -0.1700
Data Index: 7560353 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2371. Min Act: -0.1700
Data Index: 8504614 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2536. Min Act: -0.1700
Data Index: 4351574 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2701. Min Act: -0.1700
Data Index: 1919276 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2371. Min Act: -0.1700
Data Index: 5993940 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2371. Min Act: -0.1700
Data Index: 3094258 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3850. Min Range: -2.3850
Max Act: 2.2371. Min Act: -0.1700
Data Index: 2033376 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19