Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4505. Min Act: -0.0001

Data Index: 780232 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4143. Min Act: -0.0001

Data Index: 277672 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3858. Min Act: -0.0001

Data Index: 532532 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3959. Min Act: -0.0001

Data Index: 186433 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4016. Min Act: -0.0001

Data Index: 504871 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3955. Min Act: -0.0001

Data Index: 599659 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3633. Min Act: -0.0001

Data Index: 98295 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1173912 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3546. Min Act: -0.0001

Data Index: 540398 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3686. Min Act: -0.0001

Data Index: 464093 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1150018 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3458. Min Act: -0.0001

Data Index: 4768 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1025848 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1279028 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3440. Min Act: -0.0001

Data Index: 517946 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3430. Min Act: -0.0001

Data Index: 494733 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3341. Min Act: -0.0001

Data Index: 369012 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3394. Min Act: -0.0001

Data Index: 371638 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3370. Min Act: -0.0001

Data Index: 806754 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3175. Min Act: 0.0000

Data Index: 1303383 (C4 (Web Text))

Max Activating Token Index: 884