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

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

Neuron 1174 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: 1.0314. Min Range: -1.0314

Max Act: 1.0314. Min Act: -0.0001

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 1.0314. Min Range: -1.0314

Max Act: 1.0253. Min Act: -0.0001

Data Index: 609126 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.0314. Min Range: -1.0314

Max Act: 1.0089. Min Act: -0.0001

Data Index: 206049 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.0314. Min Range: -1.0314

Max Act: 1.0081. Min Act: -0.0001

Data Index: 276889 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.9724. Min Act: -0.0001

Data Index: 1214334 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.9972. Min Act: -0.0001

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8832. Min Act: -0.0001

Data Index: 607376 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.9320. Min Act: -0.0001

Data Index: 34970 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1325909 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1174080 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8957. Min Act: -0.0001

Data Index: 1070636 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8918. Min Act: -0.0001

Data Index: 361047 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8530. Min Act: -0.0001

Data Index: 199268 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8764. Min Act: -0.0001

Data Index: 345222 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8970. Min Act: -0.0001

Data Index: 700074 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8397. Min Act: -0.0001

Data Index: 441710 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8878. Min Act: -0.0001

Data Index: 160327 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.9140. Min Act: -0.0001

Data Index: 230375 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1201408 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 1.0314. Min Range: -1.0314

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1238894 (C4 (Web Text))

Max Activating Token Index: 580