Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5318 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1351768 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1264759 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4885. Min Act: -0.0000

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3507. Min Act: -0.0000

Data Index: 798992 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.2556. Min Act: -0.0000

Data Index: 299701 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.1484. Min Act: -0.0000

Data Index: 940102 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.1016. Min Act: -0.0000

Data Index: 843997 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0890. Min Act: -0.0000

Data Index: 185300 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0557. Min Act: -0.0000

Data Index: 105129 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0383. Min Act: -0.0000

Data Index: 197778 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0340. Min Act: -0.0000

Data Index: 420193 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9501. Min Act: -0.0000

Data Index: 851622 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0022. Min Act: -0.0000

Data Index: 307274 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9934. Min Act: -0.0000

Data Index: 921205 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1125036 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0275. Min Act: -0.0000

Data Index: 574541 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9551. Min Act: -0.0000

Data Index: 279356 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9481. Min Act: -0.0000

Data Index: 753958 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9363. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0084. Min Act: -0.0000

Data Index: 201150 (C4 (Web Text))

Max Activating Token Index: 340