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

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

Neuron 4581 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0262. Min Range: -1.0262

Max Act: 1.0097. Min Act: -0.0000

Data Index: 964029 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.0262. Min Range: -1.0262

Max Act: 1.0262. Min Act: -0.0000

Data Index: 870889 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8507. Min Act: -0.0000

Data Index: 761129 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1142418 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8665. Min Act: -0.0000

Data Index: 931958 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1144096 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8416. Min Act: -0.0000

Data Index: 775410 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8110. Min Act: -0.0000

Data Index: 21452 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1240757 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1205795 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7890. Min Act: -0.0000

Data Index: 26263 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7918. Min Act: -0.0000

Data Index: 560474 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7614. Min Act: -0.0000

Data Index: 934121 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.8069. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7714. Min Act: -0.0000

Data Index: 494747 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7670. Min Act: -0.0000

Data Index: 568232 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7472. Min Act: -0.0000

Data Index: 853124 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1312059 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7647. Min Act: -0.0000

Data Index: 289160 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.0262. Min Range: -1.0262

Max Act: 0.7333. Min Act: -0.0000

Data Index: 226095 (C4 (Web Text))

Max Activating Token Index: 714