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

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

Neuron 370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1094. Min Range: -4.1094

Max Act: 4.1094. Min Act: -0.0000

Data Index: 1344512 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.1094. Min Range: -4.1094

Max Act: 4.0402. Min Act: -0.0000

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 4.1094. Min Range: -4.1094

Max Act: 4.0103. Min Act: -0.0000

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7718. Min Act: -0.0000

Data Index: 747780 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.8683. Min Act: -0.0000

Data Index: 769061 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.8067. Min Act: -0.0000

Data Index: 1265241 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7923. Min Act: -0.0000

Data Index: 328587 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7648. Min Act: -0.0000

Data Index: 86885 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7211. Min Act: -0.0000

Data Index: 87371 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.8523. Min Act: -0.0000

Data Index: 1142222 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.4936. Min Act: -0.0000

Data Index: 472432 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.4743. Min Act: -0.0000

Data Index: 1164688 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.6332. Min Act: -0.0000

Data Index: 419859 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.6329. Min Act: -0.0000

Data Index: 408528 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7713. Min Act: -0.0000

Data Index: 1024353 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.4430. Min Act: -0.0000

Data Index: 537981 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.7120. Min Act: -0.0000

Data Index: 119139 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.5409. Min Act: -0.0000

Data Index: 1054773 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.5234. Min Act: -0.0000

Data Index: 136951 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 4.1094. Min Range: -4.1094

Max Act: 3.5349. Min Act: -0.0000

Data Index: 278877 (C4 (Web Text))

Max Activating Token Index: 572