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

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

Neuron 1284 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: 0.6417. Min Range: -0.6417

Max Act: 0.6383. Min Act: -0.0000

Data Index: 949436 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1020114 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5816. Min Act: -0.0000

Data Index: 464635 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1694 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6417. Min Act: -0.0001

Data Index: 722664 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.6124. Min Act: -0.0000

Data Index: 648167 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5872. Min Act: -0.0000

Data Index: 42903 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4989. Min Act: -0.0001

Data Index: 693846 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1277345 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5505. Min Act: -0.0000

Data Index: 389056 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1171931 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5191. Min Act: -0.0001

Data Index: 985181 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4669. Min Act: -0.0001

Data Index: 665320 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4515. Min Act: -0.0001

Data Index: 505002 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4321. Min Act: -0.0000

Data Index: 456698 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4134. Min Act: -0.0000

Data Index: 659041 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.3965. Min Act: -0.0000

Data Index: 930094 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4162. Min Act: -0.0000

Data Index: 928691 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.3329. Min Act: -0.0000

Data Index: 322101 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4029. Min Act: -0.0001

Data Index: 1003503 (C4 (Web Text))

Max Activating Token Index: 852