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

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

Neuron 4503 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.2274. Min Act: -0.0000

Data Index: 1338456 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0708. Min Act: 0.0000

Data Index: 801294 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1303703 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0866. Min Act: -0.0000

Data Index: 822964 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9818. Min Act: 0.0000

Data Index: 128540 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0287. Min Act: -0.0000

Data Index: 40339 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9316. Min Act: -0.0000

Data Index: 75827 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 2.2274. Min Range: -2.2274

Max Act: 2.0850. Min Act: -0.0000

Data Index: 94122 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8972. Min Act: -0.0000

Data Index: 987244 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8959. Min Act: -0.0000

Data Index: 1148107 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8978. Min Act: -0.0000

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.9712. Min Act: 0.0000

Data Index: 1183942 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8671. Min Act: -0.0000

Data Index: 48928 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8468. Min Act: -0.0000

Data Index: 378292 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8112. Min Act: -0.0000

Data Index: 723945 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.8352. Min Act: -0.0000

Data Index: 560457 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7895. Min Act: -0.0000

Data Index: 63759 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.6879. Min Act: -0.0000

Data Index: 501937 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1244167 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 2.2274. Min Range: -2.2274

Max Act: 1.7301. Min Act: -0.0000

Data Index: 563469 (C4 (Web Text))

Max Activating Token Index: 539