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

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

Neuron 4089 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: 0.9509. Min Range: -0.9509

Max Act: 0.9509. Min Act: -0.0002

Data Index: 1356312 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8613. Min Act: -0.0002

Data Index: 12294 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8110. Min Act: -0.0002

Data Index: 215369 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7982. Min Act: -0.0001

Data Index: 1312105 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8649. Min Act: -0.0002

Data Index: 487765 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7995. Min Act: -0.0002

Data Index: 463736 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7523. Min Act: -0.0001

Data Index: 543691 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7509. Min Act: -0.0002

Data Index: 1347583 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7716. Min Act: -0.0002

Data Index: 1095691 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7800. Min Act: -0.0001

Data Index: 260753 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7283. Min Act: -0.0002

Data Index: 855824 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7577. Min Act: -0.0002

Data Index: 1156712 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7542. Min Act: -0.0001

Data Index: 1060210 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7224. Min Act: -0.0002

Data Index: 1125762 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.6206. Min Act: -0.0002

Data Index: 478412 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7061. Min Act: -0.0001

Data Index: 516650 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7118. Min Act: -0.0002

Data Index: 11172 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7140. Min Act: -0.0001

Data Index: 239330 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1538409 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8066. Min Act: -0.0001

Data Index: 1465097 (Python Code)

Max Activating Token Index: 883