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

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

Neuron 647 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: 1.6334. Min Range: -1.6334

Max Act: 1.6334. Min Act: -0.0001

Data Index: 74728 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.5720. Min Act: -0.0001

Data Index: 400993 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.5488. Min Act: -0.0001

Data Index: 1309420 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.4238. Min Act: -0.0001

Data Index: 858200 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.4020. Min Act: -0.0001

Data Index: 551123 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.2032. Min Act: -0.0001

Data Index: 1237276 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.2736. Min Act: -0.0001

Data Index: 637943 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.1946. Min Act: -0.0001

Data Index: 90424 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.1652. Min Act: -0.0001

Data Index: 1355806 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.1293. Min Act: -0.0001

Data Index: 1308725 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0074. Min Act: -0.0001

Data Index: 356223 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0808. Min Act: -0.0001

Data Index: 984367 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.1564. Min Act: -0.0001

Data Index: 1172603 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.1456. Min Act: -0.0001

Data Index: 852361 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0045. Min Act: -0.0001

Data Index: 398477 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.6334. Min Range: -1.6334

Max Act: 0.9945. Min Act: -0.0001

Data Index: 540930 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0059. Min Act: -0.0001

Data Index: 954589 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0350. Min Act: -0.0001

Data Index: 1131648 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 1.6334. Min Range: -1.6334

Max Act: 1.0947. Min Act: -0.0001

Data Index: 1034389 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.6334. Min Range: -1.6334

Max Act: 0.9403. Min Act: -0.0001

Data Index: 1272167 (C4 (Web Text))

Max Activating Token Index: 579