Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 764 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0006

Data Index: 53066 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0630. Min Act: -0.0006

Data Index: 765351 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0569. Min Act: -0.0006

Data Index: 1325467 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0549. Min Act: -0.0006

Data Index: 663353 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0564. Min Act: -0.0006

Data Index: 467153 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0528. Min Act: -0.0006

Data Index: 34425 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0483. Min Act: -0.0006

Data Index: 745083 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0506. Min Act: -0.0006

Data Index: 1097713 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0487. Min Act: -0.0006

Data Index: 411222 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0507. Min Act: -0.0006

Data Index: 220369 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0474. Min Act: -0.0006

Data Index: 486171 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1248212 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0447. Min Act: -0.0006

Data Index: 814838 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0478. Min Act: -0.0006

Data Index: 101240 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0458. Min Act: -0.0006

Data Index: 172697 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0455. Min Act: -0.0006

Data Index: 294833 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0458. Min Act: -0.0006

Data Index: 820266 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1298656 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0438. Min Act: -0.0006

Data Index: 791412 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0467. Min Act: -0.0006

Data Index: 710636 (C4 (Web Text))

Max Activating Token Index: 295