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

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

Neuron 1218 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: 0.9658. Min Range: -0.9658

Max Act: 0.9658. Min Act: -0.0001

Data Index: 268060 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9212. Min Act: -0.0001

Data Index: 741575 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9484. Min Act: -0.0001

Data Index: 447008 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1292641 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9191. Min Act: -0.0001

Data Index: 1120100 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9150. Min Act: -0.0001

Data Index: 1359295 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9109. Min Act: -0.0001

Data Index: 658269 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8658. Min Act: -0.0001

Data Index: 343042 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8599. Min Act: -0.0001

Data Index: 13631 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.9068. Min Act: -0.0001

Data Index: 955079 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8429. Min Act: -0.0001

Data Index: 900031 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8397. Min Act: -0.0001

Data Index: 406039 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8618. Min Act: -0.0000

Data Index: 95531 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8645. Min Act: -0.0001

Data Index: 696469 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8401. Min Act: -0.0001

Data Index: 402857 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8459. Min Act: -0.0001

Data Index: 658695 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1335092 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8289. Min Act: -0.0001

Data Index: 225202 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8283. Min Act: -0.0001

Data Index: 655098 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.9658. Min Range: -0.9658

Max Act: 0.8561. Min Act: -0.0001

Data Index: 710512 (C4 (Web Text))

Max Activating Token Index: 358