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

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

Neuron 3248 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.9162. Min Act: -0.0000

Data Index: 372410 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.1328. Min Range: -2.1328

Max Act: 2.1328. Min Act: -0.0000

Data Index: 560906 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.5418. Min Act: -0.0000

Data Index: 815168 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1074870 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.1739. Min Act: -0.0000

Data Index: 253106 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.1387. Min Act: -0.0000

Data Index: 234257 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.0794. Min Act: -0.0000

Data Index: 135343 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 2.1328. Min Range: -2.1328

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1116121 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.9675. Min Act: -0.0000

Data Index: 783527 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.9685. Min Act: -0.0000

Data Index: 111501 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.9346. Min Act: -0.0000

Data Index: 256783 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.8675. Min Act: -0.0000

Data Index: 573510 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.7758. Min Act: -0.0000

Data Index: 969432 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.7284. Min Act: -0.0000

Data Index: 846984 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.8135. Min Act: -0.0000

Data Index: 508918 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.6684. Min Act: -0.0000

Data Index: 233317 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1033841 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.7285. Min Act: -0.0000

Data Index: 606620 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1510098 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 2.1328. Min Range: -2.1328

Max Act: 0.6795. Min Act: -0.0000

Data Index: 918928 (C4 (Web Text))

Max Activating Token Index: 382