Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1453. Min Act: -0.0004

Data Index: 1449158 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1261. Min Act: -0.0003

Data Index: 1547310 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1241. Min Act: -0.0003

Data Index: 1544985 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1329. Min Act: -0.0003

Data Index: 1627965 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1303. Min Act: -0.0003

Data Index: 1562216 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1234. Min Act: -0.0003

Data Index: 1459523 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1243. Min Act: -0.0003

Data Index: 1619582 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1275. Min Act: -0.0003

Data Index: 1547513 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1224. Min Act: -0.0003

Data Index: 1113438 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1189. Min Act: -0.0004

Data Index: 1433599 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1309. Min Act: -0.0003

Data Index: 1460417 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1632803 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1481002 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1180. Min Act: -0.0003

Data Index: 625137 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1203. Min Act: -0.0003

Data Index: 1545385 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1172600 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1081. Min Act: -0.0003

Data Index: 1584291 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1361191 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1182. Min Act: -0.0002

Data Index: 353056 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1180. Min Act: -0.0003

Data Index: 413239 (C4 (Web Text))

Max Activating Token Index: 102