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

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

Neuron 2204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1603852 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1379506 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4644. Min Act: -0.0001

Data Index: 123198 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4381. Min Act: -0.0001

Data Index: 1038706 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4327. Min Act: -0.0001

Data Index: 168039 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4222. Min Act: -0.0001

Data Index: 845245 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1014487 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4081. Min Act: -0.0001

Data Index: 1383583 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3867. Min Act: -0.0001

Data Index: 536188 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3890. Min Act: -0.0001

Data Index: 24620 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3647. Min Act: -0.0001

Data Index: 486 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1109210 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1075314 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3779. Min Act: -0.0001

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3364. Min Act: -0.0001

Data Index: 382147 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3592. Min Act: -0.0001

Data Index: 964009 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3789. Min Act: -0.0001

Data Index: 1309894 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3680. Min Act: -0.0001

Data Index: 170033 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3537. Min Act: -0.0001

Data Index: 141792 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3568. Min Act: -0.0001

Data Index: 978473 (C4 (Web Text))

Max Activating Token Index: 517