Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1294 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4294. Min Range: -3.4294

Max Act: 3.4294. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.8070. Min Act: -0.0000

Data Index: 69808 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.9398. Min Act: -0.0000

Data Index: 438266 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.4294. Min Range: -3.4294

Max Act: 3.2045. Min Act: -0.0000

Data Index: 1233368 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.6791. Min Act: -0.0000

Data Index: 626526 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.6473. Min Act: -0.0000

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.5371. Min Act: -0.0000

Data Index: 1163931 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.3222. Min Act: -0.0000

Data Index: 360205 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.3250. Min Act: -0.0000

Data Index: 590059 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.9736. Min Act: -0.0000

Data Index: 716833 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.6197. Min Act: -0.0000

Data Index: 1311058 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.2317. Min Act: -0.0000

Data Index: 1098 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.3057. Min Act: -0.0000

Data Index: 933463 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.1484. Min Act: -0.0000

Data Index: 1137220 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 3.4294. Min Range: -3.4294

Max Act: 1.9658. Min Act: -0.0000

Data Index: 1236285 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 3.4294. Min Range: -3.4294

Max Act: 2.5386. Min Act: -0.0000

Data Index: 1192484 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 3.4294. Min Range: -3.4294

Max Act: 1.9291. Min Act: -0.0000

Data Index: 769692 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 3.4294. Min Range: -3.4294

Max Act: 1.7716. Min Act: -0.0000

Data Index: 341340 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 3.4294. Min Range: -3.4294

Max Act: 1.7651. Min Act: -0.0000

Data Index: 691723 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 3.4294. Min Range: -3.4294

Max Act: 1.5515. Min Act: -0.0000

Data Index: 92220 (C4 (Web Text))

Max Activating Token Index: 732