Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3541. Min Act: -0.0002

Data Index: 571053 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3635. Min Act: -0.0001

Data Index: 901288 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3458. Min Act: -0.0001

Data Index: 561427 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1243464 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3497. Min Act: -0.0002

Data Index: 173836 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3379. Min Act: -0.0002

Data Index: 1114659 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3181. Min Act: -0.0001

Data Index: 202657 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3018. Min Act: -0.0002

Data Index: 470546 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1326345 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1225905 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3142. Min Act: -0.0001

Data Index: 429090 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2840. Min Act: -0.0001

Data Index: 471624 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3207. Min Act: -0.0002

Data Index: 826004 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3192. Min Act: -0.0002

Data Index: 654070 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1051908 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3155. Min Act: -0.0002

Data Index: 344418 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3048. Min Act: -0.0001

Data Index: 555788 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3002. Min Act: -0.0002

Data Index: 1052863 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2583. Min Act: -0.0001

Data Index: 671242 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3100. Min Act: -0.0002

Data Index: 1069268 (C4 (Web Text))

Max Activating Token Index: 665