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

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

Neuron 2666 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.8528. Min Act: -0.0000

Data Index: 47685 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.4674. Min Act: -0.0000

Data Index: 677055 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.3192. Min Act: -0.0000

Data Index: 495277 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.1838. Min Act: -0.0000

Data Index: 281293 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.0450. Min Act: -0.0000

Data Index: 837096 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.9525. Min Act: -0.0000

Data Index: 70443 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.0573. Min Act: -0.0000

Data Index: 275376 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.0403. Min Act: -0.0000

Data Index: 839813 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.9865. Min Act: -0.0000

Data Index: 7170 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 3.8528. Min Range: -3.8528

Max Act: 3.0063. Min Act: -0.0000

Data Index: 1237096 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.9093. Min Act: -0.0000

Data Index: 379689 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.8199. Min Act: -0.0000

Data Index: 1072058 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.9064. Min Act: -0.0000

Data Index: 905552 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7433. Min Act: -0.0000

Data Index: 201178 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7121. Min Act: -0.0000

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7739. Min Act: -0.0000

Data Index: 609181 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7638. Min Act: -0.0000

Data Index: 131980 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7628. Min Act: -0.0000

Data Index: 991438 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.7506. Min Act: -0.0000

Data Index: 144683 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.8528. Min Range: -3.8528

Max Act: 2.5823. Min Act: -0.0000

Data Index: 1283691 (C4 (Web Text))

Max Activating Token Index: 420