Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.5371. Min Act: -0.0000

Data Index: 351952 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.2474. Min Act: -0.0000

Data Index: 35751 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1183. Min Act: -0.0001

Data Index: 258089 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.2246. Min Act: -0.0001

Data Index: 1112318 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1995. Min Act: -0.0001

Data Index: 578426 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1225. Min Act: -0.0001

Data Index: 920428 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1239820 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1826. Min Act: -0.0000

Data Index: 297522 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1049. Min Act: -0.0001

Data Index: 468555 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1571. Min Act: -0.0001

Data Index: 698638 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1318277 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.0105. Min Act: -0.0001

Data Index: 705331 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1036. Min Act: -0.0001

Data Index: 748583 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1084. Min Act: -0.0001

Data Index: 1190174 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1347196 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.0668. Min Act: -0.0000

Data Index: 804638 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.0978. Min Act: -0.0000

Data Index: 19232 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1184329 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.0540. Min Act: -0.0001

Data Index: 917872 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.5371. Min Range: -1.5371

Max Act: 1.0338. Min Act: -0.0000

Data Index: 124501 (C4 (Web Text))

Max Activating Token Index: 55