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

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

Neuron 4661 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: 2.2842. Min Range: -2.2842

Max Act: 2.1702. Min Act: -0.0000

Data Index: 597122 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.2842. Min Act: -0.0000

Data Index: 14551 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1100139 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1125224 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.6096. Min Act: -0.0000

Data Index: 899302 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.0640. Min Act: -0.0000

Data Index: 242845 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.9273. Min Act: -0.0000

Data Index: 756634 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.1381. Min Act: -0.0000

Data Index: 39243 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.0207. Min Act: -0.0000

Data Index: 1272832 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.9435. Min Act: -0.0000

Data Index: 229156 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 2.2842. Min Range: -2.2842

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1060973 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.8249. Min Act: -0.0000

Data Index: 751559 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.8268. Min Act: -0.0000

Data Index: 751517 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.9243. Min Act: -0.0000

Data Index: 900380 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.8183. Min Act: -0.0000

Data Index: 116692 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.9006. Min Act: -0.0000

Data Index: 665278 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.7939. Min Act: -0.0000

Data Index: 268552 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.8625. Min Act: -0.0000

Data Index: 1263947 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.7626. Min Act: -0.0000

Data Index: 892523 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 2.2842. Min Range: -2.2842

Max Act: 1.8658. Min Act: -0.0000

Data Index: 188368 (C4 (Web Text))

Max Activating Token Index: 831