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

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

Neuron 2115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.6640. Min Act: -0.0000

Data Index: 923963 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1195079 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.2277. Min Act: -0.0000

Data Index: 880500 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.2743. Min Act: -0.0000

Data Index: 971739 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.1933. Min Act: -0.0000

Data Index: 279650 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.1383. Min Act: -0.0000

Data Index: 612130 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1209369 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1613700 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0110. Min Act: -0.0000

Data Index: 630444 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0213. Min Act: -0.0000

Data Index: 267554 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0501. Min Act: -0.0000

Data Index: 918085 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9584. Min Act: -0.0000

Data Index: 353831 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9631. Min Act: -0.0000

Data Index: 686981 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1195992 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9199. Min Act: -0.0000

Data Index: 407312 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9355. Min Act: -0.0000

Data Index: 431936 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1335109 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.6640. Min Range: -1.6640

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1455370 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 1.6640. Min Range: -1.6640

Max Act: 1.0541. Min Act: -0.0000

Data Index: 527599 (C4 (Web Text))

Max Activating Token Index: 900