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

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

Neuron 1857 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: 3.4434. Min Range: -3.4434

Max Act: 3.4434. Min Act: -0.0000

Data Index: 744050 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.6093. Min Act: -0.0000

Data Index: 109927 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.0730. Min Act: -0.0000

Data Index: 252223 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.1389. Min Act: -0.0000

Data Index: 219206 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.9962. Min Act: -0.0000

Data Index: 1033004 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.9021. Min Act: -0.0001

Data Index: 877209 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.1127. Min Act: -0.0000

Data Index: 1189889 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.0363. Min Act: -0.0000

Data Index: 1002450 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.8953. Min Act: -0.0000

Data Index: 291227 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1014987 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.8279. Min Act: -0.0000

Data Index: 262839 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7907. Min Act: -0.0000

Data Index: 572954 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.8858. Min Act: -0.0000

Data Index: 1170733 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.6903. Min Act: -0.0000

Data Index: 842241 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7149. Min Act: -0.0001

Data Index: 474358 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7581. Min Act: -0.0000

Data Index: 143295 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7527. Min Act: -0.0000

Data Index: 282445 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7234. Min Act: -0.0000

Data Index: 696189 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.7484. Min Act: -0.0000

Data Index: 644917 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 3.4434. Min Range: -3.4434

Max Act: 1.6663. Min Act: -0.0000

Data Index: 356600 (C4 (Web Text))

Max Activating Token Index: 606