Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1126110 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2587. Min Act: -0.0001

Data Index: 774008 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2339. Min Act: -0.0001

Data Index: 284557 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2265. Min Act: -0.0001

Data Index: 101669 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2321. Min Act: -0.0001

Data Index: 199884 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2333. Min Act: -0.0001

Data Index: 294995 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2337. Min Act: -0.0000

Data Index: 171013 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2321. Min Act: -0.0000

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1308550 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2334. Min Act: -0.0001

Data Index: 872567 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2170. Min Act: -0.0001

Data Index: 792943 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2152. Min Act: -0.0001

Data Index: 636055 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2208. Min Act: -0.0000

Data Index: 908522 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2000. Min Act: -0.0001

Data Index: 230840 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2150. Min Act: -0.0001

Data Index: 270856 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1990. Min Act: -0.0001

Data Index: 655648 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2051. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1983. Min Act: -0.0001

Data Index: 276405 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2002. Min Act: -0.0001

Data Index: 579106 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1186497 (C4 (Web Text))

Max Activating Token Index: 387