Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0001

Data Index: 241592 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2989. Min Act: -0.0001

Data Index: 196662 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2602. Min Act: -0.0001

Data Index: 347722 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2561. Min Act: -0.0001

Data Index: 119917 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1220465 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2078. Min Act: -0.0001

Data Index: 242811 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2448. Min Act: -0.0001

Data Index: 609334 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2252. Min Act: -0.0001

Data Index: 645933 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2389. Min Act: -0.0001

Data Index: 905664 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1960. Min Act: -0.0001

Data Index: 710884 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2224. Min Act: -0.0001

Data Index: 833128 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1910. Min Act: -0.0001

Data Index: 598980 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2125. Min Act: -0.0001

Data Index: 126631 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1982. Min Act: -0.0001

Data Index: 569390 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2003. Min Act: -0.0001

Data Index: 254489 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1441801 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1282029 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2126. Min Act: -0.0001

Data Index: 10530 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1081446 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1869. Min Act: -0.0001

Data Index: 261601 (C4 (Web Text))

Max Activating Token Index: 885