Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0655. Min Range: -6.0655
Max Act: 6.0655. Min Act: -0.1700
Data Index: 8087688 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0655. Min Range: -6.0655
Max Act: 6.0342. Min Act: -0.1700
Data Index: 4206390 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.8467. Min Act: -0.1700
Data Index: 7500959 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.7530. Min Act: -0.1700
Data Index: 4614368 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.7217. Min Act: -0.1700
Data Index: 1551702 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.6905. Min Act: -0.1700
Data Index: 8031708 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.6905. Min Act: -0.1700
Data Index: 8525356 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.6280. Min Act: -0.1700
Data Index: 3570581 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.6592. Min Act: -0.1700
Data Index: 83360 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.6592. Min Act: -0.1700
Data Index: 5821979 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5967. Min Act: -0.1700
Data Index: 3799882 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5342. Min Act: -0.1700
Data Index: 7949614 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5342. Min Act: -0.1700
Data Index: 2884262 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5342. Min Act: -0.1700
Data Index: 5260760 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5030. Min Act: -0.1700
Data Index: 677392 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5030. Min Act: -0.1700
Data Index: 1237435 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.5030. Min Act: -0.1700
Data Index: 7189123 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.4717. Min Act: -0.1700
Data Index: 3714470 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.4717. Min Act: -0.1700
Data Index: 991155 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0655. Min Range: -6.0655
Max Act: 5.4405. Min Act: -0.1700
Data Index: 4074049 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19