Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5205 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.2036. Min Act: -0.1700
Data Index: 3707815 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.1724. Min Act: -0.1700
Data Index: 986739 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.1411. Min Act: -0.1700
Data Index: 1646573 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.1099. Min Act: -0.1700
Data Index: 2491440 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.0474. Min Act: -0.1700
Data Index: 2296744 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2036. Min Range: -6.2036
Max Act: 6.0161. Min Act: -0.1700
Data Index: 6279808 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.9536. Min Act: -0.1700
Data Index: 1074078 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.9536. Min Act: -0.1700
Data Index: 3135797 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7174875 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3473025 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8911. Min Act: -0.1700
Data Index: 6728526 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.9224. Min Act: -0.1700
Data Index: 2880513 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8911. Min Act: -0.1700
Data Index: 4549979 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4162330 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8599. Min Act: -0.1700
Data Index: 778312 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8286. Min Act: -0.1700
Data Index: 5861404 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8286. Min Act: -0.1700
Data Index: 6115027 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8286. Min Act: -0.1700
Data Index: 1811386 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.8286. Min Act: -0.1700
Data Index: 3819629 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2036. Min Range: -6.2036
Max Act: 5.7974. Min Act: -0.1700
Data Index: 3520596 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19