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

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

Neuron 1639 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0688. Min Act: -0.0001

Data Index: 1331097 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9204. Min Act: -0.0001

Data Index: 26113 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0520. Min Act: -0.0001

Data Index: 1334723 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0477. Min Act: -0.0001

Data Index: 505366 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0284. Min Act: -0.0001

Data Index: 345803 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9728. Min Act: -0.0001

Data Index: 948978 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9480. Min Act: -0.0001

Data Index: 409373 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9774. Min Act: -0.0001

Data Index: 243902 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8430. Min Act: -0.0001

Data Index: 408861 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9729. Min Act: -0.0001

Data Index: 934361 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7215. Min Act: -0.0001

Data Index: 715227 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9901. Min Act: -0.0001

Data Index: 1308932 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9234. Min Act: -0.0001

Data Index: 375732 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9070. Min Act: -0.0001

Data Index: 530814 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9275. Min Act: -0.0001

Data Index: 883166 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9552. Min Act: -0.0001

Data Index: 1209247 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9668. Min Act: -0.0001

Data Index: 422213 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.6401. Min Act: -0.0001

Data Index: 584613 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9935. Min Act: -0.0001

Data Index: 1000662 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9016. Min Act: -0.0001

Data Index: 122211 (C4 (Web Text))

Max Activating Token Index: 28