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

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

Neuron 71 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.3727. Min Act: -0.0001

Data Index: 420708 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.3360. Min Act: -0.0002

Data Index: 969113 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.3159. Min Act: -0.0001

Data Index: 161921 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.2228. Min Act: -0.0001

Data Index: 499331 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1311. Min Act: -0.0001

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1435. Min Act: -0.0001

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0791. Min Act: -0.0001

Data Index: 1214992 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0084. Min Act: -0.0002

Data Index: 184053 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1333. Min Act: -0.0001

Data Index: 735965 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1281. Min Act: -0.0002

Data Index: 135672 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1818. Min Act: -0.0001

Data Index: 439343 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0545. Min Act: -0.0002

Data Index: 987457 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0706. Min Act: -0.0001

Data Index: 1085759 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1131. Min Act: -0.0001

Data Index: 1900 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0537. Min Act: -0.0002

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1277. Min Act: -0.0002

Data Index: 1120527 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1149. Min Act: -0.0002

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.1443. Min Act: -0.0001

Data Index: 1174614 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0724. Min Act: -0.0001

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.3727. Min Range: -1.3727

Max Act: 1.0118. Min Act: -0.0001

Data Index: 581993 (C4 (Web Text))

Max Activating Token Index: 963