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

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

Neuron 257 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.3260. Min Act: -0.0001

Data Index: 143343 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.4969. Min Act: -0.0001

Data Index: 762322 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2773. Min Act: -0.0001

Data Index: 711531 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.1503. Min Act: -0.0001

Data Index: 480473 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2120. Min Act: -0.0001

Data Index: 261524 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0319. Min Act: -0.0001

Data Index: 1258112 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.2655. Min Act: -0.0001

Data Index: 536925 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.1465. Min Act: -0.0001

Data Index: 1204428 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.1424. Min Act: -0.0001

Data Index: 73222 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0754. Min Act: -0.0001

Data Index: 34152 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0404. Min Act: -0.0001

Data Index: 211330 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.4969. Min Range: -1.4969

Max Act: 0.9937. Min Act: -0.0001

Data Index: 765488 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0106. Min Act: -0.0001

Data Index: 348677 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.4969. Min Range: -1.4969

Max Act: 0.9979. Min Act: -0.0001

Data Index: 380932 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0557. Min Act: -0.0001

Data Index: 1086613 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0760. Min Act: -0.0001

Data Index: 935415 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0514. Min Act: -0.0001

Data Index: 1193036 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.4969. Min Range: -1.4969

Max Act: 1.0152. Min Act: -0.0001

Data Index: 880812 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 1.4969. Min Range: -1.4969

Max Act: 0.9421. Min Act: -0.0001

Data Index: 443035 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.4969. Min Range: -1.4969

Max Act: 0.9085. Min Act: -0.0001

Data Index: 163525 (C4 (Web Text))

Max Activating Token Index: 858