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

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

Neuron 1993 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.5528. Min Act: -0.0000

Data Index: 1307651 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.5862. Min Act: -0.0000

Data Index: 460999 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1352019 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1257439 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1074635 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4795. Min Act: -0.0000

Data Index: 699027 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4755. Min Act: -0.0000

Data Index: 972905 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.4272. Min Act: -0.0000

Data Index: 352737 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2459. Min Act: -0.0000

Data Index: 670000 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2152. Min Act: -0.0000

Data Index: 450143 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2854. Min Act: -0.0000

Data Index: 780946 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1020568 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.3425. Min Act: -0.0000

Data Index: 928773 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2587. Min Act: -0.0000

Data Index: 749943 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1107196 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1455294 (Python Code)

Max Activating Token Index: 967

Text #16

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1316072 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2221. Min Act: -0.0000

Data Index: 485465 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.1602. Min Act: -0.0000

Data Index: 781388 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.5862. Min Range: -1.5862

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1089552 (C4 (Web Text))

Max Activating Token Index: 962