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

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

Neuron 4485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1302417 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1011055 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2738. Min Act: -0.0000

Data Index: 935366 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2748. Min Act: -0.0000

Data Index: 285697 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2902. Min Act: -0.0000

Data Index: 818519 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2602. Min Act: -0.0000

Data Index: 796697 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2534. Min Act: -0.0000

Data Index: 216969 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1037399 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1256982 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2429. Min Act: -0.0000

Data Index: 181018 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1045129 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2384. Min Act: -0.0000

Data Index: 71492 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2318. Min Act: -0.0000

Data Index: 556867 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1562119 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1234748 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1292297 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1189554 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2116. Min Act: -0.0000

Data Index: 332663 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2285. Min Act: -0.0000

Data Index: 914177 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1232536 (C4 (Web Text))

Max Activating Token Index: 672