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

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

Neuron 3197 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.8471. Min Act: -0.0000

Data Index: 1105497 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.6606. Min Act: -0.0000

Data Index: 996217 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1192548 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.5504. Min Act: -0.0000

Data Index: 938060 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1335599 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1345433 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1054518 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.4809. Min Act: -0.0000

Data Index: 384277 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3948. Min Act: -0.0000

Data Index: 93211 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3520. Min Act: -0.0000

Data Index: 198924 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.2732. Min Act: -0.0000

Data Index: 837119 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3430. Min Act: -0.0000

Data Index: 583176 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3120. Min Act: -0.0000

Data Index: 623113 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.2910. Min Act: -0.0000

Data Index: 648676 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.2987. Min Act: -0.0000

Data Index: 580074 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1308298 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.2663. Min Act: -0.0000

Data Index: 355644 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3308. Min Act: -0.0000

Data Index: 526613 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.1646. Min Act: -0.0000

Data Index: 49708 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.8471. Min Range: -1.8471

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1024709 (C4 (Web Text))

Max Activating Token Index: 319