Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1292 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.1786. Min Act: -0.0000

Data Index: 489041 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.9921. Min Act: -0.0000

Data Index: 177677 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.9197. Min Act: -0.0000

Data Index: 298328 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0518. Min Act: -0.0000

Data Index: 673145 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.7408. Min Act: -0.0000

Data Index: 962563 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.7236. Min Act: -0.0000

Data Index: 334088 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0237. Min Act: -0.0000

Data Index: 515224 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.5818. Min Act: -0.0000

Data Index: 1068318 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.1350. Min Act: -0.0000

Data Index: 243264 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.7349. Min Act: -0.0000

Data Index: 44570 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.8534. Min Act: -0.0000

Data Index: 1165485 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1564524 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.7585. Min Act: -0.0001

Data Index: 882557 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.6031. Min Act: -0.0000

Data Index: 698606 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.5512. Min Act: -0.0000

Data Index: 1335262 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.2745. Min Act: -0.0000

Data Index: 1243886 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.5219. Min Act: -0.0000

Data Index: 58675 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.3971. Min Act: -0.0000

Data Index: 1382999 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.6316. Min Act: -0.0000

Data Index: 1141373 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.3277. Min Act: -0.0000

Data Index: 1404789 (Python Code)

Max Activating Token Index: 208