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

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

Neuron 1350 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: 0.1461. Min Range: -0.1461

Max Act: 0.1460. Min Act: -0.0005

Data Index: 750140 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1461. Min Act: -0.0004

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1292. Min Act: -0.0005

Data Index: 396693 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1378. Min Act: -0.0004

Data Index: 1322947 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1310. Min Act: -0.0004

Data Index: 589290 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1285. Min Act: -0.0004

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1368. Min Act: -0.0004

Data Index: 408484 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1204. Min Act: -0.0004

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1213. Min Act: -0.0004

Data Index: 310279 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1252. Min Act: -0.0004

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1234. Min Act: -0.0004

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1251. Min Act: -0.0004

Data Index: 653844 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1212. Min Act: -0.0005

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1209. Min Act: -0.0004

Data Index: 107426 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1213. Min Act: -0.0005

Data Index: 1063901 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1186. Min Act: -0.0004

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1170. Min Act: -0.0005

Data Index: 1299243 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1164. Min Act: -0.0004

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1139. Min Act: -0.0004

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1145. Min Act: -0.0005

Data Index: 1304207 (C4 (Web Text))

Max Activating Token Index: 550