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

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

Neuron 2475 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: 0.7134. Min Range: -0.7134

Max Act: 0.7134. Min Act: -0.0001

Data Index: 910460 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.7115. Min Act: -0.0002

Data Index: 1093798 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6838. Min Act: -0.0002

Data Index: 345377 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6880. Min Act: -0.0002

Data Index: 926240 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.7092. Min Act: -0.0002

Data Index: 1161848 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6669. Min Act: -0.0002

Data Index: 78659 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6818. Min Act: -0.0002

Data Index: 1107392 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6753. Min Act: -0.0002

Data Index: 11764 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6735. Min Act: -0.0002

Data Index: 518432 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6783. Min Act: -0.0002

Data Index: 699298 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6745. Min Act: -0.0002

Data Index: 1326798 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6724. Min Act: -0.0002

Data Index: 2176 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6084. Min Act: -0.0002

Data Index: 1282940 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6231. Min Act: -0.0002

Data Index: 501823 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6706. Min Act: -0.0002

Data Index: 961095 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6464. Min Act: -0.0002

Data Index: 1345032 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6450. Min Act: -0.0002

Data Index: 998740 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6466. Min Act: -0.0002

Data Index: 446978 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1004705 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6564. Min Act: -0.0001

Data Index: 54324 (C4 (Web Text))

Max Activating Token Index: 915