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

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

Neuron 3982 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4383. Min Range: -5.4383

Max Act: 5.4383. Min Act: -0.0000

Data Index: 1199212 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.8044. Min Act: -0.0000

Data Index: 279119 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.6666. Min Act: -0.0000

Data Index: 352204 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.3689. Min Act: -0.0000

Data Index: 1257511 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.3543. Min Act: -0.0000

Data Index: 25829 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.1122. Min Act: -0.0000

Data Index: 615019 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.2297. Min Act: -0.0000

Data Index: 1073510 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.1923. Min Act: -0.0000

Data Index: 911593 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.0266. Min Act: -0.0000

Data Index: 289294 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.3509. Min Act: -0.0000

Data Index: 454907 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.9603. Min Act: -0.0000

Data Index: 492432 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.9200. Min Act: -0.0000

Data Index: 630477 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 5.4383. Min Range: -5.4383

Max Act: 4.0222. Min Act: -0.0000

Data Index: 645051 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.9918. Min Act: -0.0000

Data Index: 86351 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.8288. Min Act: -0.0000

Data Index: 905320 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.9557. Min Act: -0.0000

Data Index: 73049 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.7781. Min Act: -0.0000

Data Index: 1221259 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.7881. Min Act: -0.0000

Data Index: 335351 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.7558. Min Act: -0.0000

Data Index: 555141 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 5.4383. Min Range: -5.4383

Max Act: 3.8991. Min Act: -0.0000

Data Index: 1252067 (C4 (Web Text))

Max Activating Token Index: 77