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

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

Neuron 4190 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7015. Min Range: -2.7015

Max Act: 2.7015. Min Act: -0.0000

Data Index: 1534661 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 2.7015. Min Range: -2.7015

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1565685 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1377531 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.9414. Min Act: -0.0000

Data Index: 464424 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.9161. Min Act: -0.0000

Data Index: 740970 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.9146. Min Act: -0.0000

Data Index: 985140 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 2.7015. Min Range: -2.7015

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1435901 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1418006 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1228406 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.2965. Min Act: -0.0000

Data Index: 198974 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1245203 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.2293. Min Act: -0.0000

Data Index: 532925 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1148714 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1147062 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0746. Min Act: -0.0000

Data Index: 476318 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0015. Min Act: -0.0000

Data Index: 984150 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0668. Min Act: -0.0000

Data Index: 773943 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0334. Min Act: -0.0000

Data Index: 849916 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 2.7015. Min Range: -2.7015

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1206518 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 2.7015. Min Range: -2.7015

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1134259 (C4 (Web Text))

Max Activating Token Index: 673