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

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

Neuron 1474 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: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1196210 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1599. Min Act: -0.0001

Data Index: 228105 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1472. Min Act: -0.0001

Data Index: 20972 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1413. Min Act: -0.0001

Data Index: 905071 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1020259 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1130468 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1431. Min Act: -0.0001

Data Index: 81120 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1320. Min Act: -0.0001

Data Index: 236272 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1313. Min Act: -0.0001

Data Index: 37148 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1040418 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1388. Min Act: -0.0001

Data Index: 312478 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1206998 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1037141 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1721 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1142. Min Act: -0.0001

Data Index: 959357 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1269. Min Act: -0.0001

Data Index: 608996 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1254. Min Act: -0.0001

Data Index: 85960 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1150126 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1232. Min Act: -0.0001

Data Index: 707422 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1339436 (C4 (Web Text))

Max Activating Token Index: 647