Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.7768. Min Act: -0.1700
Data Index: 458884 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.7143. Min Act: -0.1700
Data Index: 1381648 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.6205. Min Act: -0.1700
Data Index: 804536 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.6518. Min Act: -0.1700
Data Index: 3033167 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.6518. Min Act: -0.1700
Data Index: 6057607 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.6205. Min Act: -0.1700
Data Index: 3441458 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4955. Min Act: -0.1700
Data Index: 496241 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4955. Min Act: -0.1700
Data Index: 8259305 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3218802 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4643. Min Act: -0.1700
Data Index: 4461475 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4643. Min Act: -0.1700
Data Index: 6165668 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2398281 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 8338224 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4330. Min Act: -0.1700
Data Index: 6254577 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 8203649 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 5083390 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7828830 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3705. Min Act: -0.1700
Data Index: 551941 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3705. Min Act: -0.1700
Data Index: 3153914 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3393. Min Act: -0.1700
Data Index: 1879758 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19