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

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

Neuron 409 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6658. Min Act: -0.0003

Data Index: 1314414 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6559. Min Act: -0.0003

Data Index: 436733 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6322. Min Act: -0.0003

Data Index: 1092070 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6096. Min Act: -0.0003

Data Index: 1346538 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6306. Min Act: -0.0003

Data Index: 715707 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6563. Min Act: -0.0003

Data Index: 813355 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5996. Min Act: -0.0003

Data Index: 894154 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6358. Min Act: -0.0003

Data Index: 1119479 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5949. Min Act: -0.0003

Data Index: 1255091 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4874. Min Act: -0.0003

Data Index: 380826 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6122. Min Act: -0.0003

Data Index: 82325 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5873. Min Act: -0.0004

Data Index: 352614 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5689. Min Act: -0.0003

Data Index: 1259451 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5863. Min Act: -0.0003

Data Index: 593640 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5244. Min Act: -0.0003

Data Index: 485843 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6003. Min Act: -0.0003

Data Index: 1319301 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5805. Min Act: -0.0004

Data Index: 939102 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5931. Min Act: -0.0003

Data Index: 1235117 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.5714. Min Act: -0.0003

Data Index: 722664 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6059. Min Act: -0.0003

Data Index: 379292 (C4 (Web Text))

Max Activating Token Index: 40