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

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

Neuron 3839 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1901. Min Act: -0.0000

Data Index: 457074 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1702. Min Act: -0.0001

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1499. Min Act: -0.0001

Data Index: 267188 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1476. Min Act: -0.0001

Data Index: 148889 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1519. Min Act: -0.0001

Data Index: 347863 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1442. Min Act: -0.0001

Data Index: 761482 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1318. Min Act: -0.0000

Data Index: 222605 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1361. Min Act: -0.0001

Data Index: 20769 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1105. Min Act: -0.0001

Data Index: 701010 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1250202 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1248. Min Act: -0.0001

Data Index: 677641 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1254. Min Act: -0.0001

Data Index: 286002 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1370. Min Act: -0.0001

Data Index: 345208 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1219. Min Act: -0.0001

Data Index: 873184 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1324. Min Act: -0.0001

Data Index: 387735 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1295. Min Act: -0.0000

Data Index: 505332 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1320. Min Act: -0.0001

Data Index: 881680 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1334. Min Act: -0.0001

Data Index: 374559 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1227. Min Act: -0.0001

Data Index: 623534 (C4 (Web Text))

Max Activating Token Index: 220