Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2035 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0006

Data Index: 863965 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0629. Min Act: -0.0006

Data Index: 280754 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0586. Min Act: -0.0006

Data Index: 632379 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0570. Min Act: -0.0006

Data Index: 387995 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0564. Min Act: -0.0006

Data Index: 863287 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1082123 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0535. Min Act: -0.0006

Data Index: 238845 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0536. Min Act: -0.0006

Data Index: 113639 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0535. Min Act: -0.0006

Data Index: 1114254 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0593. Min Act: -0.0006

Data Index: 569390 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0534. Min Act: -0.0006

Data Index: 717701 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0554. Min Act: -0.0006

Data Index: 781189 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0552. Min Act: -0.0006

Data Index: 536865 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0536. Min Act: -0.0006

Data Index: 141573 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0581. Min Act: -0.0006

Data Index: 1147331 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1031236 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0542. Min Act: -0.0006

Data Index: 718065 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1105598 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0521. Min Act: -0.0006

Data Index: 680378 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0504. Min Act: -0.0006

Data Index: 1070314 (C4 (Web Text))

Max Activating Token Index: 508