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

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

Neuron 1911 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: 1.4434. Min Range: -1.4434

Max Act: 1.4434. Min Act: -0.0000

Data Index: 563974 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1031785 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1293784 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1022264 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1666. Min Act: -0.0000

Data Index: 51366 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1841. Min Act: -0.0000

Data Index: 852978 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0974. Min Act: -0.0000

Data Index: 204454 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1708. Min Act: -0.0000

Data Index: 486807 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0765. Min Act: -0.0000

Data Index: 816165 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1834. Min Act: -0.0000

Data Index: 923066 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0583. Min Act: -0.0000

Data Index: 98952 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1235. Min Act: -0.0000

Data Index: 241062 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1316386 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1173420 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0718. Min Act: -0.0000

Data Index: 593262 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0814. Min Act: -0.0000

Data Index: 611924 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1043. Min Act: -0.0000

Data Index: 358895 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4434. Min Range: -1.4434

Max Act: 0.9995. Min Act: -0.0000

Data Index: 194959 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1340545 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0502. Min Act: -0.0000

Data Index: 853011 (C4 (Web Text))

Max Activating Token Index: 856