Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6322 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 2591962 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.1147. Min Act: -0.1700
Data Index: 2495754 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2709. Min Range: -6.2709
Max Act: 6.0209. Min Act: -0.1700
Data Index: 7353792 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9897. Min Act: -0.1700
Data Index: 3174775 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9897. Min Act: -0.1700
Data Index: 4815548 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 2000843 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 6405471 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9584. Min Act: -0.1700
Data Index: 5458909 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.9272. Min Act: -0.1700
Data Index: 952427 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8959. Min Act: -0.1700
Data Index: 3814397 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8959. Min Act: -0.1700
Data Index: 3626263 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8959. Min Act: -0.1700
Data Index: 4298580 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8647. Min Act: -0.1700
Data Index: 3830140 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8647. Min Act: -0.1700
Data Index: 8628653 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7701255 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2595832 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8022. Min Act: -0.1700
Data Index: 5499059 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8022. Min Act: -0.1700
Data Index: 1089448 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8022. Min Act: -0.1700
Data Index: 1051585 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2709. Min Range: -6.2709
Max Act: 5.8022. Min Act: -0.1700
Data Index: 8527218 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19