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

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

Neuron 1545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0601. Min Act: -0.0002

Data Index: 983510 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1191461 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0585. Min Act: -0.0002

Data Index: 474506 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0554. Min Act: -0.0002

Data Index: 924919 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0583. Min Act: -0.0002

Data Index: 721123 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1210139 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0586. Min Act: -0.0002

Data Index: 145120 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0563. Min Act: -0.0002

Data Index: 174445 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1116400 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0519. Min Act: -0.0002

Data Index: 479422 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0555. Min Act: -0.0002

Data Index: 297813 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0541. Min Act: -0.0002

Data Index: 844026 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0505. Min Act: -0.0002

Data Index: 464153 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0527. Min Act: -0.0002

Data Index: 379186 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0563. Min Act: -0.0002

Data Index: 371376 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1053953 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1025028 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0545. Min Act: -0.0002

Data Index: 574487 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0530. Min Act: -0.0002

Data Index: 473944 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0536. Min Act: -0.0002

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 320