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

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

Neuron 1246 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: 2.3263. Min Range: -2.3263

Max Act: 2.2764. Min Act: -0.0000

Data Index: 850139 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.1286. Min Act: -0.0000

Data Index: 1147724 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.3263. Min Act: -0.0000

Data Index: 944838 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9328. Min Act: -0.0000

Data Index: 333897 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.2938. Min Act: -0.0000

Data Index: 1108964 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1024310 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.1009. Min Act: -0.0000

Data Index: 471328 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1056774 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.0551. Min Act: -0.0000

Data Index: 191570 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9147. Min Act: -0.0000

Data Index: 900241 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9571. Min Act: -0.0000

Data Index: 466889 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9932. Min Act: -0.0000

Data Index: 355951 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9944. Min Act: -0.0000

Data Index: 292308 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.8616. Min Act: -0.0000

Data Index: 779362 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.3263. Min Range: -2.3263

Max Act: 2.0392. Min Act: -0.0000

Data Index: 957928 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9765. Min Act: -0.0000

Data Index: 793619 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.8958. Min Act: -0.0000

Data Index: 429599 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.8305. Min Act: -0.0000

Data Index: 849303 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.9253. Min Act: -0.0000

Data Index: 549313 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 2.3263. Min Range: -2.3263

Max Act: 1.8626. Min Act: -0.0000

Data Index: 78434 (C4 (Web Text))

Max Activating Token Index: 936