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

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

Neuron 2318 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: 0.2212. Min Range: -0.2212

Max Act: 0.2212. Min Act: -0.0001

Data Index: 628650 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1244788 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1985. Min Act: -0.0001

Data Index: 56318 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1880. Min Act: -0.0001

Data Index: 10025 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1814. Min Act: -0.0000

Data Index: 798513 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1933. Min Act: -0.0001

Data Index: 794379 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1754. Min Act: -0.0001

Data Index: 341235 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1922. Min Act: -0.0001

Data Index: 423307 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1765. Min Act: -0.0001

Data Index: 986590 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1679. Min Act: -0.0001

Data Index: 837260 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1297835 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1700. Min Act: -0.0001

Data Index: 485748 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1644. Min Act: -0.0001

Data Index: 892823 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1178347 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1649. Min Act: -0.0001

Data Index: 408164 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1562. Min Act: -0.0001

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1626. Min Act: -0.0001

Data Index: 287655 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1155454 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1343443 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1194173 (C4 (Web Text))

Max Activating Token Index: 801