Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5508 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.7678. Min Act: -0.1700
Data Index: 2067372 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.6428. Min Act: -0.1700
Data Index: 853955 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.6428. Min Act: -0.1700
Data Index: 1026009 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.5490. Min Act: -0.1700
Data Index: 125130 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4865. Min Act: -0.1700
Data Index: 1625336 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4553. Min Act: -0.1700
Data Index: 2813922 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4553. Min Act: -0.1700
Data Index: 1629114 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4865. Min Act: -0.1700
Data Index: 2374723 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4865. Min Act: -0.1700
Data Index: 4139900 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4553. Min Act: -0.1700
Data Index: 869997 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4240. Min Act: -0.1700
Data Index: 2422036 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4240. Min Act: -0.1700
Data Index: 6755824 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4553. Min Act: -0.1700
Data Index: 5198920 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.4240. Min Act: -0.1700
Data Index: 5418181 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3928. Min Act: -0.1700
Data Index: 4796457 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3928. Min Act: -0.1700
Data Index: 2218711 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3615. Min Act: -0.1700
Data Index: 7976935 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3928. Min Act: -0.1700
Data Index: 1866483 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3928. Min Act: -0.1700
Data Index: 8210707 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7678. Min Range: -6.7678
Max Act: 6.3928. Min Act: -0.1700
Data Index: 4854730 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19