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

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

Neuron 2781 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.6877. Min Act: -0.0001

Data Index: 637552 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.2415. Min Act: -0.0001

Data Index: 265227 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.1337. Min Act: -0.0001

Data Index: 452907 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0949. Min Act: -0.0001

Data Index: 1108584 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0682. Min Act: -0.0001

Data Index: 265279 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0285. Min Act: -0.0001

Data Index: 1415876 (Python Code)

Max Activating Token Index: 864

Text #6

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9985. Min Act: -0.0001

Data Index: 1421812 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0693. Min Act: -0.0001

Data Index: 882925 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9763. Min Act: -0.0001

Data Index: 1060452 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0387. Min Act: -0.0001

Data Index: 1099522 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0386. Min Act: -0.0001

Data Index: 297448 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0542. Min Act: -0.0001

Data Index: 1632167 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 1.6877. Min Range: -1.6877

Max Act: 1.0310. Min Act: -0.0001

Data Index: 629812 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9908. Min Act: -0.0001

Data Index: 871493 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9856. Min Act: -0.0001

Data Index: 134760 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9511. Min Act: -0.0001

Data Index: 1424641 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1002826 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9128. Min Act: -0.0001

Data Index: 1225835 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9542. Min Act: -0.0001

Data Index: 767516 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.6877. Min Range: -1.6877

Max Act: 0.9212. Min Act: -0.0001

Data Index: 90089 (C4 (Web Text))

Max Activating Token Index: 893