Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.1770. Min Act: -0.0001

Data Index: 931000 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.1881. Min Act: -0.0001

Data Index: 1312170 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.1881. Min Range: -1.1881

Max Act: 1.0242. Min Act: -0.0001

Data Index: 767925 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9552. Min Act: -0.0001

Data Index: 157144 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9329. Min Act: -0.0001

Data Index: 1309465 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9651. Min Act: -0.0001

Data Index: 735597 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9240. Min Act: -0.0001

Data Index: 201398 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8611. Min Act: -0.0001

Data Index: 169085 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9062. Min Act: -0.0001

Data Index: 396460 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9329. Min Act: -0.0001

Data Index: 128094 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.9142. Min Act: -0.0001

Data Index: 506414 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8610. Min Act: -0.0001

Data Index: 609250 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8853. Min Act: -0.0001

Data Index: 466159 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.7960. Min Act: -0.0001

Data Index: 300434 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8193. Min Act: -0.0001

Data Index: 158631 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8709. Min Act: -0.0001

Data Index: 1250561 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8163. Min Act: -0.0001

Data Index: 1334863 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8667. Min Act: -0.0001

Data Index: 596296 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8312. Min Act: -0.0001

Data Index: 230381 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.1881. Min Range: -1.1881

Max Act: 0.8660. Min Act: -0.0001

Data Index: 455384 (C4 (Web Text))

Max Activating Token Index: 631