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

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

Neuron 2032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.4292. Min Act: -0.0001

Data Index: 1291711 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.4629. Min Act: -0.0000

Data Index: 958034 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.5031. Min Act: -0.0001

Data Index: 698501 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.3600. Min Act: -0.0000

Data Index: 220888 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2419. Min Act: -0.0000

Data Index: 623786 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2470. Min Act: -0.0000

Data Index: 328065 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.3403. Min Act: -0.0001

Data Index: 702201 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2130. Min Act: -0.0000

Data Index: 1020530 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.1444. Min Act: -0.0001

Data Index: 223323 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.3678. Min Act: -0.0001

Data Index: 451080 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.1941. Min Act: -0.0000

Data Index: 224434 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2579. Min Act: -0.0001

Data Index: 31226 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2467. Min Act: -0.0000

Data Index: 160808 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2384. Min Act: -0.0001

Data Index: 866786 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1212933 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.2268. Min Act: -0.0000

Data Index: 151681 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.1316. Min Act: -0.0000

Data Index: 103524 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.1049. Min Act: -0.0000

Data Index: 189630 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.0861. Min Act: -0.0000

Data Index: 948165 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 2.5031. Min Range: -2.5031

Max Act: 2.0767. Min Act: -0.0001

Data Index: 350769 (C4 (Web Text))

Max Activating Token Index: 940