Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3229 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 9.1346. Min Range: -9.1346

Max Act: 9.1346. Min Act: -0.0000

Data Index: 408081 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 9.1346. Min Range: -9.1346

Max Act: 7.9545. Min Act: -0.0000

Data Index: 266073 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 9.1346. Min Range: -9.1346

Max Act: 7.1244. Min Act: -0.0000

Data Index: 668152 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 9.1346. Min Range: -9.1346

Max Act: 7.1745. Min Act: -0.0000

Data Index: 868726 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.4680. Min Act: -0.0000

Data Index: 1288633 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 9.1346. Min Range: -9.1346

Max Act: 7.3839. Min Act: -0.0000

Data Index: 819194 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.0716. Min Act: -0.0000

Data Index: 529657 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.4206. Min Act: -0.0000

Data Index: 636040 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.8147. Min Act: -0.0000

Data Index: 941026 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.6967. Min Act: -0.0000

Data Index: 1335707 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.1072. Min Act: -0.0000

Data Index: 1274670 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.4296. Min Act: -0.0000

Data Index: 1251706 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.1310. Min Act: -0.0000

Data Index: 132397 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.9210. Min Act: -0.0000

Data Index: 583600 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 9.1346. Min Range: -9.1346

Max Act: 4.9446. Min Act: -0.0000

Data Index: 615849 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 9.1346. Min Range: -9.1346

Max Act: 6.5243. Min Act: -0.0000

Data Index: 213353 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.0056. Min Act: -0.0000

Data Index: 749592 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.0373. Min Act: -0.0000

Data Index: 404818 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 9.1346. Min Range: -9.1346

Max Act: 4.7389. Min Act: -0.0000

Data Index: 962423 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 9.1346. Min Range: -9.1346

Max Act: 5.5832. Min Act: -0.0000

Data Index: 1040547 (C4 (Web Text))

Max Activating Token Index: 143