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

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

Neuron 3050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0326. Min Range: -1.0326

Max Act: 1.0326. Min Act: -0.0000

Data Index: 707422 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.8058. Min Act: -0.0001

Data Index: 843765 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1059909 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7792. Min Act: -0.0000

Data Index: 552805 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7235. Min Act: -0.0000

Data Index: 908871 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6733. Min Act: -0.0000

Data Index: 387797 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7038. Min Act: -0.0000

Data Index: 315872 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6976. Min Act: -0.0000

Data Index: 358751 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1177883 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6424. Min Act: -0.0001

Data Index: 571262 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6603. Min Act: -0.0000

Data Index: 145069 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6779. Min Act: -0.0000

Data Index: 88145 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1055953 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6225. Min Act: -0.0000

Data Index: 12330 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1185226 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6344. Min Act: -0.0000

Data Index: 997555 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6111. Min Act: -0.0001

Data Index: 742840 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.5957. Min Act: -0.0000

Data Index: 4359 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6156. Min Act: -0.0001

Data Index: 165355 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6233. Min Act: -0.0000

Data Index: 529253 (C4 (Web Text))

Max Activating Token Index: 984