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

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

Neuron 5229 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1195634 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6503. Min Act: -0.0000

Data Index: 550892 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5783. Min Act: -0.0000

Data Index: 547108 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4900. Min Act: -0.0000

Data Index: 835621 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5797. Min Act: -0.0000

Data Index: 274349 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5910. Min Act: -0.0000

Data Index: 425785 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5652. Min Act: -0.0000

Data Index: 194309 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5648. Min Act: -0.0000

Data Index: 752640 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5162. Min Act: -0.0000

Data Index: 335997 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1510606 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5539. Min Act: -0.0000

Data Index: 450416 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5668. Min Act: -0.0000

Data Index: 547237 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5327. Min Act: -0.0000

Data Index: 253511 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1340896 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1194510 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4887. Min Act: -0.0000

Data Index: 333631 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1561467 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5174. Min Act: -0.0000

Data Index: 42696 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4999. Min Act: -0.0000

Data Index: 985306 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.4970. Min Act: -0.0000

Data Index: 963651 (C4 (Web Text))

Max Activating Token Index: 289