Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.6102. Min Range: -10.6102
Max Act: 10.6102. Min Act: -0.1700
Data Index: 4979782 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6102. Min Range: -10.6102
Max Act: 10.5477. Min Act: -0.1699
Data Index: 141435 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6102. Min Range: -10.6102
Max Act: 10.3602. Min Act: -0.1697
Data Index: 5627010 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6102. Min Range: -10.6102
Max Act: 10.0477. Min Act: -0.1700
Data Index: 4814230 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6102. Min Range: -10.6102
Max Act: 10.0477. Min Act: -0.1698
Data Index: 1380975 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.8602. Min Act: -0.1700
Data Index: 947715 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.8602. Min Act: -0.1700
Data Index: 2177684 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.9227. Min Act: -0.1700
Data Index: 6169303 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.9227. Min Act: -0.1700
Data Index: 4950330 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.9852. Min Act: -0.1700
Data Index: 5393377 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.9227. Min Act: -0.1700
Data Index: 3248808 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7977. Min Act: -0.1700
Data Index: 3982082 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7977. Min Act: -0.1699
Data Index: 2483873 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7977. Min Act: -0.1700
Data Index: 5393359 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7977. Min Act: -0.1700
Data Index: 3697203 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7977. Min Act: -0.1700
Data Index: 529886 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.7352. Min Act: -0.1700
Data Index: 7423505 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.6727. Min Act: -0.1700
Data Index: 2752991 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.6727. Min Act: -0.1700
Data Index: 929659 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6102. Min Range: -10.6102
Max Act: 9.6727. Min Act: -0.1700
Data Index: 542292 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19