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

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

Neuron 4503 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.7555. Min Act: -0.0000

Data Index: 683567 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.7146. Min Act: -0.0000

Data Index: 440798 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.8920. Min Act: -0.0000

Data Index: 769186 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.3808. Min Act: -0.0000

Data Index: 493548 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.3831. Min Act: -0.0000

Data Index: 198892 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.2020. Min Act: -0.0000

Data Index: 41297 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.1402. Min Act: -0.0000

Data Index: 382097 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.9808. Min Act: 0.0000

Data Index: 992777 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.9740. Min Act: -0.0000

Data Index: 676 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.7563. Min Act: -0.0000

Data Index: 590359 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.7505. Min Act: -0.0000

Data Index: 996833 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.8920. Min Range: -2.8920

Max Act: 2.1295. Min Act: -0.0000

Data Index: 52790 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.6618. Min Act: -0.0000

Data Index: 22182 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.8328. Min Act: 0.0000

Data Index: 1221619 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.7119. Min Act: -0.0000

Data Index: 1134319 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1020561 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1066995 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.5798. Min Act: -0.0000

Data Index: 164192 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.5531. Min Act: -0.0000

Data Index: 219162 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 2.8920. Min Range: -2.8920

Max Act: 1.4705. Min Act: -0.0000

Data Index: 643001 (C4 (Web Text))

Max Activating Token Index: 371