Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1525. Min Range: -8.1525
Max Act: 8.1525. Min Act: -0.1700
Data Index: 7305897 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1525. Min Range: -8.1525
Max Act: 8.0588. Min Act: -0.1700
Data Index: 7478991 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.8713. Min Act: -0.1700
Data Index: 7305896 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.1213. Min Act: -0.1700
Data Index: 3417949 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.0900. Min Act: -0.1700
Data Index: 1568748 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.0275. Min Act: -0.1700
Data Index: 3447383 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.0275. Min Act: -0.1700
Data Index: 1196668 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9650. Min Act: -0.1700
Data Index: 6852377 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9963. Min Act: -0.1700
Data Index: 1724847 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.0275. Min Act: -0.1700
Data Index: 1846957 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9963. Min Act: -0.1700
Data Index: 5055156 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9963. Min Act: -0.1700
Data Index: 5495803 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1525. Min Range: -8.1525
Max Act: 7.0275. Min Act: -0.1700
Data Index: 5103327 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9338. Min Act: -0.1700
Data Index: 2699301 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9338. Min Act: -0.1700
Data Index: 852330 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9338. Min Act: -0.1700
Data Index: 1828267 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9025. Min Act: -0.1700
Data Index: 4520903 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.8400. Min Act: -0.1700
Data Index: 2238285 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.9025. Min Act: -0.1700
Data Index: 4591598 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1525. Min Range: -8.1525
Max Act: 6.8088. Min Act: -0.1700
Data Index: 3876894 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19