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

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

Neuron 2338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.9675. Min Act: -0.0000

Data Index: 891982 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.8633. Min Act: -0.0000

Data Index: 233935 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.5433. Min Act: -0.0000

Data Index: 1214449 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.6996. Min Act: -0.0000

Data Index: 127942 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.5777. Min Act: -0.0000

Data Index: 697258 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3612. Min Act: -0.0000

Data Index: 286826 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1327781 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.4334. Min Act: -0.0000

Data Index: 608465 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3653. Min Act: -0.0000

Data Index: 600865 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.4079. Min Act: -0.0000

Data Index: 75119 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3792. Min Act: -0.0000

Data Index: 475318 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.4503. Min Act: -0.0000

Data Index: 412606 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.4002. Min Act: -0.0000

Data Index: 300061 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3503. Min Act: -0.0000

Data Index: 309237 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3591. Min Act: -0.0000

Data Index: 457668 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1548522 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.3504. Min Act: -0.0000

Data Index: 963812 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1248047 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.2817. Min Act: -0.0000

Data Index: 575603 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.9675. Min Range: -1.9675

Max Act: 1.1631. Min Act: -0.0000

Data Index: 572500 (C4 (Web Text))

Max Activating Token Index: 465