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

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

Neuron 2434 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1547919 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1431. Min Act: -0.0001

Data Index: 616165 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1382. Min Act: -0.0001

Data Index: 105930 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1407. Min Act: -0.0001

Data Index: 55130 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1299. Min Act: -0.0001

Data Index: 472533 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1337. Min Act: -0.0001

Data Index: 934512 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1136. Min Act: -0.0001

Data Index: 435226 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1138324 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1263. Min Act: -0.0001

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1144. Min Act: -0.0001

Data Index: 629785 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1151. Min Act: -0.0001

Data Index: 278141 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1210. Min Act: -0.0001

Data Index: 6695 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1220. Min Act: -0.0001

Data Index: 479464 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1050101 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1224. Min Act: -0.0001

Data Index: 845593 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1301100 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1206. Min Act: -0.0001

Data Index: 555009 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1182. Min Act: -0.0001

Data Index: 900015 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1149173 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1177. Min Act: -0.0001

Data Index: 980332 (C4 (Web Text))

Max Activating Token Index: 149