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

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

Neuron 588 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: 0.1602. Min Range: -0.1602

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1233100 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1532. Min Act: -0.0000

Data Index: 586831 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1467. Min Act: -0.0000

Data Index: 770501 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1125076 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1565. Min Act: -0.0000

Data Index: 861222 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1283267 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1466. Min Act: -0.0000

Data Index: 557398 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1575. Min Act: -0.0000

Data Index: 523151 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1353229 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1042745 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1329. Min Act: -0.0000

Data Index: 933127 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1471429 (Python Code)

Max Activating Token Index: 979

Text #12

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1382. Min Act: -0.0001

Data Index: 754974 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1112864 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1206. Min Act: -0.0000

Data Index: 234411 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1211. Min Act: -0.0001

Data Index: 615744 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1234. Min Act: -0.0000

Data Index: 983782 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1179. Min Act: -0.0000

Data Index: 360677 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1336. Min Act: -0.0000

Data Index: 210397 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1192. Min Act: -0.0000

Data Index: 89955 (C4 (Web Text))

Max Activating Token Index: 286