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

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

Neuron 3753 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: 0.2293. Min Range: -0.2293

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1366167 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1063702 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1090699 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0000

Data Index: 541244 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1397. Min Act: -0.0001

Data Index: 888668 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1625. Min Act: -0.0000

Data Index: 419125 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1447. Min Act: -0.0000

Data Index: 618730 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1552. Min Act: -0.0001

Data Index: 146909 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1620145 (Python Code)

Max Activating Token Index: 1009

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1335. Min Act: -0.0001

Data Index: 652918 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1329. Min Act: -0.0001

Data Index: 858450 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1297. Min Act: -0.0001

Data Index: 122282 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1370866 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1264. Min Act: -0.0001

Data Index: 236634 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1468874 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1126834 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1262. Min Act: -0.0001

Data Index: 384020 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1415994 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1498913 (Python Code)

Max Activating Token Index: 821