Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5061 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1165814 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.1352. Min Act: -0.0000

Data Index: 231025 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9369. Min Act: -0.0000

Data Index: 536567 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1040183 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9928. Min Act: -0.0000

Data Index: 756798 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8261. Min Act: -0.0000

Data Index: 580908 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7815. Min Act: -0.0000

Data Index: 22369 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7707. Min Act: -0.0000

Data Index: 120829 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8546. Min Act: -0.0000

Data Index: 51262 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1115116 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7340. Min Act: -0.0000

Data Index: 574308 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6676. Min Act: -0.0000

Data Index: 172884 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7016. Min Act: -0.0000

Data Index: 831169 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6796. Min Act: -0.0000

Data Index: 935978 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6649. Min Act: -0.0000

Data Index: 465758 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6626. Min Act: -0.0000

Data Index: 894256 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6188. Min Act: -0.0000

Data Index: 947480 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.6151. Min Act: -0.0000

Data Index: 907154 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.5394. Min Act: -0.0000

Data Index: 556879 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1179793 (C4 (Web Text))

Max Activating Token Index: 748