Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.4900. Min Act: -0.1700
Data Index: 1633623 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.4588. Min Act: -0.1700
Data Index: 4792192 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.4275. Min Act: -0.1700
Data Index: 5430541 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.3025. Min Act: -0.1700
Data Index: 1582764 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.3025. Min Act: -0.1700
Data Index: 1021378 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.2713. Min Act: -0.1700
Data Index: 4644040 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.2400. Min Act: -0.1700
Data Index: 546757 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.2088. Min Act: -0.1700
Data Index: 5968990 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1775. Min Act: -0.1700
Data Index: 7299654 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 922878 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3550204 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1668336 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 8494610 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 726738 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1775. Min Act: -0.1700
Data Index: 7757930 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1775. Min Act: -0.1700
Data Index: 7539045 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 2610034 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1310796 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 629068 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4900. Min Range: -4.4900
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1198673 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19