Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1287 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1424. Min Act: -0.0005

Data Index: 225277 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1377. Min Act: -0.0005

Data Index: 812188 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1363. Min Act: -0.0005

Data Index: 1229632 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1298. Min Act: -0.0005

Data Index: 590189 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1236. Min Act: -0.0005

Data Index: 767228 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1368. Min Act: -0.0005

Data Index: 1138528 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1322. Min Act: -0.0005

Data Index: 383026 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1255. Min Act: -0.0005

Data Index: 1089196 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1252. Min Act: -0.0005

Data Index: 1260021 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1322. Min Act: -0.0005

Data Index: 409924 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1267. Min Act: -0.0005

Data Index: 135183 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1259. Min Act: -0.0005

Data Index: 350841 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1255. Min Act: -0.0005

Data Index: 699680 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1256. Min Act: -0.0005

Data Index: 417336 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1192. Min Act: -0.0005

Data Index: 144620 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1200. Min Act: -0.0005

Data Index: 603366 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1149. Min Act: -0.0005

Data Index: 492207 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1234. Min Act: -0.0005

Data Index: 908770 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1141. Min Act: -0.0005

Data Index: 420757 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1233. Min Act: -0.0005

Data Index: 560992 (C4 (Web Text))

Max Activating Token Index: 150