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

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

Neuron 2821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0038. Min Range: -1.0038

Max Act: 1.0038. Min Act: -0.0000

Data Index: 445262 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9356. Min Act: -0.0000

Data Index: 650594 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9735. Min Act: -0.0000

Data Index: 382672 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9424. Min Act: -0.0000

Data Index: 538354 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1106422 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8498. Min Act: -0.0000

Data Index: 694376 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8480. Min Act: -0.0000

Data Index: 708424 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8749. Min Act: -0.0000

Data Index: 436817 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.9113. Min Act: -0.0000

Data Index: 767488 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1589384 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8603. Min Act: -0.0000

Data Index: 526514 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1446551 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1227039 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7205. Min Act: -0.0000

Data Index: 245804 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7386. Min Act: -0.0000

Data Index: 347407 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.7111. Min Act: -0.0000

Data Index: 695147 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1601673 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.6593. Min Act: -0.0000

Data Index: 113884 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1544991 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 1.0038. Min Range: -1.0038

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1122172 (C4 (Web Text))

Max Activating Token Index: 454