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

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

Neuron 1267 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.8633. Min Act: -0.0000

Data Index: 507271 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.8417. Min Act: -0.0000

Data Index: 980665 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.4559. Min Act: -0.0000

Data Index: 673279 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.3727. Min Act: -0.0000

Data Index: 873037 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.2152. Min Act: -0.0000

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.3055. Min Act: -0.0000

Data Index: 360998 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.9565. Min Act: -0.0000

Data Index: 1080363 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.0607. Min Act: -0.0000

Data Index: 897587 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.0397. Min Act: -0.0000

Data Index: 354710 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.1658. Min Act: -0.0000

Data Index: 432975 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.8224. Min Act: -0.0000

Data Index: 285240 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1162794 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.7858. Min Act: -0.0000

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.6004. Min Act: -0.0000

Data Index: 801390 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.8770. Min Act: -0.0000

Data Index: 253502 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.5342. Min Act: -0.0000

Data Index: 496927 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.4382. Min Act: -0.0000

Data Index: 737337 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.5738. Min Act: -0.0000

Data Index: 48584 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.5517. Min Act: -0.0000

Data Index: 541041 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 4.8633. Min Range: -4.8633

Max Act: 3.3484. Min Act: -0.0000

Data Index: 803204 (C4 (Web Text))

Max Activating Token Index: 1010