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

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

Neuron 734 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: 0.2148. Min Range: -0.2148

Max Act: 0.2148. Min Act: -0.0001

Data Index: 724361 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1924. Min Act: -0.0002

Data Index: 584726 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1668. Min Act: -0.0001

Data Index: 13991 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1569. Min Act: -0.0002

Data Index: 108874 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1568. Min Act: -0.0002

Data Index: 277407 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1613. Min Act: -0.0001

Data Index: 562352 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1546. Min Act: -0.0001

Data Index: 910732 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1636. Min Act: -0.0001

Data Index: 764464 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1551. Min Act: -0.0001

Data Index: 790044 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1510. Min Act: -0.0001

Data Index: 315918 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1591. Min Act: -0.0002

Data Index: 88665 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1431. Min Act: -0.0001

Data Index: 260517 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1459. Min Act: -0.0002

Data Index: 456773 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1468. Min Act: -0.0001

Data Index: 472334 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1576767 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1438. Min Act: -0.0001

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1621. Min Act: -0.0002

Data Index: 188941 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1451. Min Act: -0.0001

Data Index: 421205 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1291. Min Act: -0.0001

Data Index: 921192 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1290. Min Act: -0.0001

Data Index: 625784 (C4 (Web Text))

Max Activating Token Index: 221