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

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

Neuron 858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8889. Min Range: -2.8889

Max Act: 2.8889. Min Act: -0.0000

Data Index: 272516 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 2.8889. Min Range: -2.8889

Max Act: 2.6916. Min Act: -0.0000

Data Index: 1333979 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 2.8889. Min Range: -2.8889

Max Act: 2.2932. Min Act: -0.0000

Data Index: 64345 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 2.8889. Min Range: -2.8889

Max Act: 2.1251. Min Act: -0.0000

Data Index: 207339 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 2.8889. Min Range: -2.8889

Max Act: 2.0790. Min Act: -0.0000

Data Index: 802793 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.9085. Min Act: -0.0000

Data Index: 933963 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.9263. Min Act: -0.0000

Data Index: 997028 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.7610. Min Act: -0.0000

Data Index: 50481 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1635234 (Python Code)

Max Activating Token Index: 282

Text #9

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.7584. Min Act: -0.0000

Data Index: 507592 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1338709 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.7231. Min Act: -0.0000

Data Index: 962141 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.6671. Min Act: -0.0000

Data Index: 783758 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.6555. Min Act: -0.0000

Data Index: 601393 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1330902 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1277750 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.5024. Min Act: -0.0000

Data Index: 156028 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.5711. Min Act: -0.0000

Data Index: 516550 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1273706 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 2.8889. Min Range: -2.8889

Max Act: 1.4693. Min Act: -0.0000

Data Index: 477440 (C4 (Web Text))

Max Activating Token Index: 192