Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.3502. Min Act: -0.1700
Data Index: 4771653 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.2564. Min Act: -0.1700
Data Index: 3555235 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 437489 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 1749519 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 1455520 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7213943 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 2167685 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 6252972 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1314. Min Act: -0.1700
Data Index: 6395161 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1314. Min Act: -0.1700
Data Index: 1148897 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 1033140 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4861111 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 1802691 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 474173 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 7640318 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4437675 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.0689. Min Act: -0.1700
Data Index: 2379340 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.0689. Min Act: -0.1700
Data Index: 3386645 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.0377. Min Act: -0.1700
Data Index: 233923 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.0689. Min Act: -0.1700
Data Index: 1985506 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19