Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 4560450 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 4722563 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.5614. Min Act: -0.1700
Data Index: 5583085 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.5302. Min Act: -0.1700
Data Index: 8251168 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.3739. Min Act: -0.1700
Data Index: 989775 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.3739. Min Act: -0.1700
Data Index: 2556901 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.3427. Min Act: -0.1700
Data Index: 4468893 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2489. Min Act: -0.1700
Data Index: 1394421 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2802. Min Act: -0.1700
Data Index: 5996320 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2489. Min Act: -0.1700
Data Index: 2651732 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2489. Min Act: -0.1700
Data Index: 2729197 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2489. Min Act: -0.1700
Data Index: 2950123 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2177. Min Act: -0.1700
Data Index: 4854746 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2177. Min Act: -0.1700
Data Index: 7353594 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2177. Min Act: -0.1700
Data Index: 5391612 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.1864. Min Act: -0.1700
Data Index: 2212511 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.1864. Min Act: -0.1700
Data Index: 303995 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.1864. Min Act: -0.1700
Data Index: 7744152 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.2177. Min Act: -0.1700
Data Index: 7283264 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5614. Min Range: -4.5614
Max Act: 4.1239. Min Act: -0.1700
Data Index: 1521239 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19