Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1014 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.6614. Min Act: -0.1700
Data Index: 16356 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.4426. Min Act: -0.1700
Data Index: 4298489 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.4114. Min Act: -0.1700
Data Index: 6894020 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.2551. Min Act: -0.1700
Data Index: 6894021 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.2864. Min Act: -0.1700
Data Index: 8201936 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.2239. Min Act: -0.1700
Data Index: 8121222 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.2551. Min Act: -0.1700
Data Index: 6598429 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.0676. Min Act: -0.1700
Data Index: 7827367 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.0364. Min Act: -0.1700
Data Index: 1944602 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.0364. Min Act: -0.1700
Data Index: 250902 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.0364. Min Act: -0.1700
Data Index: 3553172 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9739. Min Act: -0.1700
Data Index: 4681588 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6614. Min Range: -6.6614
Max Act: 6.0051. Min Act: -0.1700
Data Index: 1392457 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9739. Min Act: -0.1700
Data Index: 6874662 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9426. Min Act: -0.1700
Data Index: 4842618 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9426. Min Act: -0.1700
Data Index: 2432050 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9426. Min Act: -0.1700
Data Index: 3911112 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.8801. Min Act: -0.1700
Data Index: 3649776 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.9114. Min Act: -0.1700
Data Index: 4873233 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6614. Min Range: -6.6614
Max Act: 5.8801. Min Act: -0.1700
Data Index: 436751 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19