Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.6556. Min Act: -0.1700
Data Index: 7359497 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.5306. Min Act: -0.1700
Data Index: 263402 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6637639 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.5619. Min Act: -0.1700
Data Index: 2341140 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.4994. Min Act: -0.1700
Data Index: 5247359 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.4369. Min Act: -0.1700
Data Index: 3663458 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.4056. Min Act: -0.1700
Data Index: 502780 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3744. Min Act: -0.1700
Data Index: 8233560 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3744. Min Act: -0.1700
Data Index: 5451993 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3744. Min Act: -0.1700
Data Index: 7017497 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3431. Min Act: -0.1700
Data Index: 3019234 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3431. Min Act: -0.1700
Data Index: 729839 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3119. Min Act: -0.1700
Data Index: 6235697 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3119. Min Act: -0.1700
Data Index: 1735458 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.3431. Min Act: -0.1700
Data Index: 7811977 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.2494. Min Act: -0.1700
Data Index: 1625216 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.2181. Min Act: -0.1700
Data Index: 123087 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.2181. Min Act: -0.1700
Data Index: 2856607 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.2494. Min Act: -0.1700
Data Index: 2888890 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6556. Min Range: -5.6556
Max Act: 5.2494. Min Act: -0.1700
Data Index: 2917639 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19