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

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

Neuron 1414 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8806. Min Act: -0.0000

Data Index: 549306 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8600. Min Act: -0.0000

Data Index: 377617 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.7662. Min Act: -0.0000

Data Index: 766026 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.7177. Min Act: -0.0000

Data Index: 720992 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1074825 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6238. Min Act: -0.0000

Data Index: 282428 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1067451 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1217539 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1370472 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1182141 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1624155 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1562588 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6151. Min Act: -0.0000

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5747. Min Act: -0.0000

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6158. Min Act: -0.0000

Data Index: 729347 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5899. Min Act: -0.0000

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1595936 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5584. Min Act: -0.0000

Data Index: 899284 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.5545. Min Act: -0.0000

Data Index: 189739 (C4 (Web Text))

Max Activating Token Index: 55