Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.1439. Min Act: -0.1699
Data Index: 5774051 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.4876. Min Act: -0.1700
Data Index: 18709 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4876. Min Range: -6.4876
Max Act: 3.9563. Min Act: -0.1700
Data Index: 363588 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2689. Min Act: -0.1700
Data Index: 2508672 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0189. Min Act: -0.1281
Data Index: 677479 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2376. Min Act: -0.1700
Data Index: 5427650 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.1439. Min Act: -0.1700
Data Index: 7816742 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.1126. Min Act: -0.1700
Data Index: 893102 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2376. Min Act: 0.0468
Data Index: 5812979 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.7689. Min Act: -0.1679
Data Index: 788432 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8626. Min Act: -0.1700
Data Index: 1784478 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.1439. Min Act: -0.1699
Data Index: 1377304 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0501. Min Act: -0.1700
Data Index: 3584376 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8001. Min Act: -0.1692
Data Index: 2154700 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.7064. Min Act: -0.1700
Data Index: 5159560 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2064. Min Act: -0.1698
Data Index: 2508671 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.5501. Min Act: -0.1683
Data Index: 4849328 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.7689. Min Act: -0.1700
Data Index: 3948448 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5691902 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.0501. Min Act: -0.1700
Data Index: 4453365 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19