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

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

Neuron 4063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1491749 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4687. Min Act: -0.0000

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4865. Min Act: -0.0000

Data Index: 844098 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1414636 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1021989 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1529381 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1511181 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2253. Min Act: -0.0000

Data Index: 109616 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1498549 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1359507 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1876. Min Act: -0.0000

Data Index: 616906 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1474939 (Python Code)

Max Activating Token Index: 408

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2206. Min Act: -0.0000

Data Index: 117226 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1162499 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2482. Min Act: -0.0000

Data Index: 412280 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1951. Min Act: -0.0000

Data Index: 184816 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1555. Min Act: -0.0000

Data Index: 86116 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1482. Min Act: -0.0000

Data Index: 709903 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1260413 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1829. Min Act: -0.0000

Data Index: 505001 (C4 (Web Text))

Max Activating Token Index: 793