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

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

Neuron 4345 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: 1.0833. Min Range: -1.0833

Max Act: 1.0074. Min Act: -0.0001

Data Index: 833928 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.0833. Min Range: -1.0833

Max Act: 1.0833. Min Act: -0.0001

Data Index: 1176255 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9795. Min Act: -0.0001

Data Index: 181040 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.0833. Min Range: -1.0833

Max Act: 1.0399. Min Act: -0.0001

Data Index: 763549 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9838. Min Act: -0.0001

Data Index: 248836 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9402. Min Act: -0.0001

Data Index: 225887 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9574. Min Act: -0.0001

Data Index: 1294283 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9700. Min Act: -0.0001

Data Index: 107838 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9114. Min Act: -0.0001

Data Index: 27013 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8984. Min Act: -0.0001

Data Index: 365339 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8033. Min Act: -0.0001

Data Index: 37584 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8844. Min Act: -0.0001

Data Index: 1403867 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8559. Min Act: -0.0001

Data Index: 98151 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1096708 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8946. Min Act: -0.0001

Data Index: 262559 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.9203. Min Act: -0.0001

Data Index: 1328298 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8904. Min Act: -0.0001

Data Index: 791027 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1030693 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.8826. Min Act: -0.0001

Data Index: 743863 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.0833. Min Range: -1.0833

Max Act: 0.7299. Min Act: -0.0001

Data Index: 358639 (C4 (Web Text))

Max Activating Token Index: 742