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

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

Neuron 362 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.6696. Min Act: -0.0000

Data Index: 1329501 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.7322. Min Act: -0.0001

Data Index: 63357 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.3867. Min Act: -0.0000

Data Index: 465472 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.5892. Min Act: -0.0000

Data Index: 124954 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.5326. Min Act: -0.0001

Data Index: 463301 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.6142. Min Act: -0.0000

Data Index: 596332 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.6679. Min Act: -0.0000

Data Index: 905318 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9790. Min Act: -0.0001

Data Index: 273119 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.5584. Min Act: -0.0001

Data Index: 1144860 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9437. Min Act: -0.0001

Data Index: 403412 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.2560. Min Act: -0.0001

Data Index: 226833 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.4267. Min Act: -0.0001

Data Index: 459756 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0518. Min Act: -0.0000

Data Index: 659204 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.2703. Min Act: -0.0000

Data Index: 628716 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.1568. Min Act: -0.0001

Data Index: 1304275 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.8557. Min Act: -0.0000

Data Index: 913588 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0418. Min Act: -0.0000

Data Index: 1294620 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 2.7322. Min Range: -2.7322

Max Act: 1.9506. Min Act: -0.0000

Data Index: 155863 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.1599. Min Act: -0.0000

Data Index: 641955 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.7322. Min Range: -2.7322

Max Act: 2.0493. Min Act: -0.0001

Data Index: 201520 (C4 (Web Text))

Max Activating Token Index: 812