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

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

Neuron 1649 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: 0.0494. Min Range: -0.0494

Max Act: 0.0492. Min Act: -0.0006

Data Index: 203425 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0006

Data Index: 371226 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0458. Min Act: -0.0006

Data Index: 138620 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0484. Min Act: -0.0006

Data Index: 905597 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0482. Min Act: -0.0006

Data Index: 458964 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0446. Min Act: -0.0006

Data Index: 1232423 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1242639 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1255313 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1021888 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1036511 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0423. Min Act: -0.0006

Data Index: 132844 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 542527 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0440. Min Act: -0.0006

Data Index: 580845 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1245516 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0455. Min Act: -0.0006

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0428. Min Act: -0.0006

Data Index: 358460 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0429. Min Act: -0.0006

Data Index: 20684 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0443. Min Act: -0.0006

Data Index: 1167422 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0445. Min Act: -0.0006

Data Index: 37240 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1156425 (C4 (Web Text))

Max Activating Token Index: 313