Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4842 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0001

Data Index: 344312 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9175. Min Act: -0.0001

Data Index: 285821 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9889. Min Act: -0.0001

Data Index: 244410 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0426. Min Act: -0.0001

Data Index: 771225 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1145972 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8291. Min Act: -0.0001

Data Index: 197131 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8229. Min Act: -0.0001

Data Index: 242448 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8129. Min Act: -0.0001

Data Index: 729186 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8196. Min Act: -0.0001

Data Index: 521088 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7716. Min Act: -0.0001

Data Index: 1148865 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1175236 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8523. Min Act: -0.0001

Data Index: 1209393 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1081197 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7791. Min Act: -0.0001

Data Index: 570349 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7953. Min Act: -0.0001

Data Index: 1305739 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7520. Min Act: -0.0001

Data Index: 589467 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7491. Min Act: -0.0001

Data Index: 758399 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7734. Min Act: -0.0001

Data Index: 596395 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7710. Min Act: -0.0001

Data Index: 608571 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.6235. Min Act: -0.0001

Data Index: 69973 (C4 (Web Text))

Max Activating Token Index: 339