Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.7538. Min Act: -0.1700
Data Index: 5566543 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.7455. Min Act: -0.1700
Data Index: 1216151 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6881. Min Act: -0.1700
Data Index: 1120772 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6800. Min Act: -0.1700
Data Index: 2094473 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6800. Min Act: -0.1700
Data Index: 8242613 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6800. Min Act: -0.1700
Data Index: 4859485 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6558. Min Act: -0.1700
Data Index: 4422346 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6558. Min Act: -0.1700
Data Index: 2338725 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6558. Min Act: -0.1700
Data Index: 7647373 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6478. Min Act: -0.1700
Data Index: 4824184 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6478. Min Act: -0.1700
Data Index: 491923 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6398. Min Act: -0.1700
Data Index: 8602236 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6398. Min Act: -0.1700
Data Index: 1666860 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6398. Min Act: -0.1700
Data Index: 1571405 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6398. Min Act: -0.1700
Data Index: 7506018 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6478. Min Act: -0.1691
Data Index: 6665209 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6398. Min Act: -0.1700
Data Index: 8684026 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6318. Min Act: -0.1700
Data Index: 2525028 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6318. Min Act: -0.1700
Data Index: 602335 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7538. Min Range: -0.7538
Max Act: 0.6318. Min Act: -0.1700
Data Index: 3164761 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19