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

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

Neuron 1436 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: 3.1139. Min Range: -3.1139

Max Act: 3.1139. Min Act: -0.0000

Data Index: 94999 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.2883. Min Act: -0.0000

Data Index: 450950 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.1596. Min Act: -0.0000

Data Index: 1206422 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1225936 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.1730. Min Act: -0.0000

Data Index: 903260 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.1293. Min Act: -0.0000

Data Index: 938920 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.8654. Min Act: -0.0000

Data Index: 295351 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.9687. Min Act: -0.0000

Data Index: 713672 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.9566. Min Act: -0.0000

Data Index: 819849 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.0665. Min Act: -0.0000

Data Index: 1004508 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.9017. Min Act: -0.0000

Data Index: 363147 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 3.1139. Min Range: -3.1139

Max Act: 2.0109. Min Act: -0.0000

Data Index: 1064553 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.8783. Min Act: -0.0000

Data Index: 201380 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.8686. Min Act: -0.0000

Data Index: 695484 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.8675. Min Act: -0.0000

Data Index: 3909 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.7432. Min Act: -0.0000

Data Index: 760941 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.9343. Min Act: -0.0000

Data Index: 1264503 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1197600 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.6665. Min Act: -0.0000

Data Index: 650492 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 3.1139. Min Range: -3.1139

Max Act: 1.4607. Min Act: -0.0000

Data Index: 513360 (C4 (Web Text))

Max Activating Token Index: 240