Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3825 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7677. Min Range: -2.7677

Max Act: 2.7677. Min Act: -0.0000

Data Index: 318743 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 2.7677. Min Range: -2.7677

Max Act: 2.3606. Min Act: 0.0000

Data Index: 734222 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 2.7677. Min Range: -2.7677

Max Act: 2.3280. Min Act: -0.0000

Data Index: 650653 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 2.7677. Min Range: -2.7677

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1298919 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1264745 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.8715. Min Act: 0.0000

Data Index: 944539 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.8330. Min Act: -0.0000

Data Index: 276383 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.7248. Min Act: -0.0000

Data Index: 893722 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.8268. Min Act: 0.0000

Data Index: 1126658 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.5258. Min Act: -0.0000

Data Index: 895182 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1160318 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.6343. Min Act: -0.0000

Data Index: 954008 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1265567 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.5979. Min Act: 0.0000

Data Index: 1286864 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.4566. Min Act: -0.0000

Data Index: 312688 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.4589. Min Act: -0.0000

Data Index: 934719 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1110762 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.6147. Min Act: -0.0000

Data Index: 616833 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.5079. Min Act: 0.0000

Data Index: 541278 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 2.7677. Min Range: -2.7677

Max Act: 1.3345. Min Act: -0.0000

Data Index: 366034 (C4 (Web Text))

Max Activating Token Index: 193