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

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

Neuron 3821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4342. Min Act: -0.0000

Data Index: 28757 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4264. Min Act: -0.0000

Data Index: 478686 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3878. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3586. Min Act: -0.0000

Data Index: 841776 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1026023 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3371. Min Act: -0.0000

Data Index: 693188 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3566. Min Act: -0.0000

Data Index: 606636 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3561. Min Act: -0.0000

Data Index: 990096 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1270001 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3263. Min Act: -0.0000

Data Index: 173913 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3370. Min Act: -0.0000

Data Index: 453399 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3236. Min Act: -0.0000

Data Index: 659588 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3206. Min Act: -0.0000

Data Index: 158767 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3262. Min Act: -0.0000

Data Index: 164772 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3156. Min Act: -0.0000

Data Index: 89285 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1234453 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3215. Min Act: -0.0000

Data Index: 290992 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3002. Min Act: -0.0000

Data Index: 864383 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3232. Min Act: -0.0000

Data Index: 881916 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2967. Min Act: -0.0000

Data Index: 262946 (C4 (Web Text))

Max Activating Token Index: 920