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

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

Neuron 1080 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: 3.1290. Min Range: -3.1290

Max Act: 3.1290. Min Act: -0.0000

Data Index: 18347 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.9128. Min Act: -0.0000

Data Index: 147512 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.6985. Min Act: -0.0000

Data Index: 715065 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.8433. Min Act: -0.0000

Data Index: 691210 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5468. Min Act: -0.0000

Data Index: 241927 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5290. Min Act: -0.0000

Data Index: 574114 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3372. Min Act: -0.0000

Data Index: 1342844 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4576. Min Act: -0.0000

Data Index: 1079222 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.2963. Min Act: -0.0000

Data Index: 818100 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4075. Min Act: -0.0000

Data Index: 1154446 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1135476 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3743. Min Act: -0.0000

Data Index: 1714 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5045. Min Act: -0.0000

Data Index: 403203 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.2236. Min Act: -0.0000

Data Index: 996274 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3650. Min Act: -0.0000

Data Index: 1420226 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4844. Min Act: -0.0000

Data Index: 641316 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.5948. Min Act: -0.0000

Data Index: 491163 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.3305. Min Act: -0.0000

Data Index: 828538 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.4519. Min Act: -0.0000

Data Index: 197072 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 3.1290. Min Range: -3.1290

Max Act: 2.1806. Min Act: -0.0000

Data Index: 592864 (C4 (Web Text))

Max Activating Token Index: 73