Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4728 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2546. Min Range: -3.2546
Max Act: 3.2546. Min Act: -0.1700
Data Index: 27550 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8918. Min Act: -0.1700
Data Index: 5692494 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.9076. Min Act: -0.1700
Data Index: 3975966 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8600. Min Act: -0.1700
Data Index: 4315188 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8759. Min Act: -0.1700
Data Index: 8832044 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8759. Min Act: -0.1700
Data Index: 1201917 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8600. Min Act: -0.1700
Data Index: 455733 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8282. Min Act: -0.1700
Data Index: 694883 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8123. Min Act: -0.1700
Data Index: 6943498 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.8123. Min Act: -0.1700
Data Index: 8136005 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7964. Min Act: -0.1700
Data Index: 7206766 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7964. Min Act: -0.1700
Data Index: 2874429 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7805. Min Act: -0.1700
Data Index: 4464819 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7964. Min Act: -0.1700
Data Index: 3683293 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7805. Min Act: -0.1700
Data Index: 7056783 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7805. Min Act: -0.1700
Data Index: 4140718 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7645. Min Act: -0.1700
Data Index: 4574296 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7805. Min Act: -0.1700
Data Index: 4073428 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7645. Min Act: -0.1700
Data Index: 5022840 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2546. Min Range: -3.2546
Max Act: 2.7805. Min Act: -0.1700
Data Index: 8686714 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19