Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3799 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6630. Min Act: -0.1700
Data Index: 7349793 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6630. Min Act: -0.1700
Data Index: 7660032 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6317. Min Act: -0.1700
Data Index: 417472 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6005. Min Act: -0.1700
Data Index: 6579887 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6005. Min Act: -0.1699
Data Index: 8427807 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.6005. Min Act: -0.1700
Data Index: 6946146 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5692. Min Act: -0.1700
Data Index: 8365033 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5692. Min Act: -0.1700
Data Index: 1793015 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5692. Min Act: -0.1700
Data Index: 5566167 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5692. Min Act: -0.1700
Data Index: 1804445 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5067. Min Act: -0.1700
Data Index: 5350003 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5380. Min Act: -0.1700
Data Index: 6344348 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5380. Min Act: -0.1700
Data Index: 2929019 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7221393 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7788066 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.5067. Min Act: -0.1700
Data Index: 1113282 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.4755. Min Act: -0.1700
Data Index: 3072305 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.4755. Min Act: -0.1700
Data Index: 2464655 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.4442. Min Act: -0.1700
Data Index: 6401140 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6630. Min Range: -5.6630
Max Act: 5.4755. Min Act: -0.1700
Data Index: 2733105 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19