Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3475. Min Act: -0.0000

Data Index: 896627 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3279. Min Act: -0.0000

Data Index: 960896 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3003. Min Act: -0.0000

Data Index: 173035 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2925. Min Act: -0.0000

Data Index: 752753 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3259. Min Act: -0.0000

Data Index: 316340 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2832. Min Act: -0.0001

Data Index: 300056 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1143438 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2725. Min Act: -0.0000

Data Index: 110703 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2619. Min Act: -0.0000

Data Index: 644657 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2754. Min Act: -0.0000

Data Index: 249199 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1227856 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1128756 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1251118 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2541. Min Act: -0.0000

Data Index: 7708 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2687. Min Act: -0.0000

Data Index: 668723 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2433. Min Act: -0.0000

Data Index: 987311 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2587. Min Act: -0.0000

Data Index: 579951 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2502. Min Act: -0.0000

Data Index: 144548 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2497. Min Act: -0.0000

Data Index: 135530 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2460. Min Act: -0.0001

Data Index: 444800 (C4 (Web Text))

Max Activating Token Index: 245