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

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

Neuron 854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0703. Min Range: -3.0703

Max Act: 3.0703. Min Act: -0.0000

Data Index: 895805 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9794. Min Act: -0.0000

Data Index: 571421 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9813. Min Act: -0.0000

Data Index: 1323187 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.6938. Min Act: -0.0000

Data Index: 951744 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.8229. Min Act: -0.0000

Data Index: 116841 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.7031. Min Act: -0.0000

Data Index: 399007 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9076. Min Act: -0.0000

Data Index: 899309 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.6925. Min Act: -0.0000

Data Index: 57877 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1246450 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.4619. Min Act: -0.0000

Data Index: 352857 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.5722. Min Act: -0.0000

Data Index: 1228468 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.4223. Min Act: -0.0000

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.6499. Min Act: -0.0000

Data Index: 460916 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.5061. Min Act: -0.0000

Data Index: 245804 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.2952. Min Act: -0.0000

Data Index: 457842 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1341240 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.2511. Min Act: -0.0000

Data Index: 102775 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.7158. Min Act: -0.0000

Data Index: 551451 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.4437. Min Act: -0.0000

Data Index: 872520 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.5680. Min Act: -0.0000

Data Index: 119238 (C4 (Web Text))

Max Activating Token Index: 48