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

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

Neuron 1505 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0309. Min Range: -5.0309

Max Act: 5.0309. Min Act: -0.0000

Data Index: 1177120 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 5.0309. Min Range: -5.0309

Max Act: 4.6142. Min Act: -0.0000

Data Index: 101214 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 5.0309. Min Range: -5.0309

Max Act: 4.6042. Min Act: -0.0000

Data Index: 659919 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 5.0309. Min Range: -5.0309

Max Act: 4.1354. Min Act: -0.0000

Data Index: 635891 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 5.0309. Min Range: -5.0309

Max Act: 4.0354. Min Act: -0.0001

Data Index: 1328183 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.8187. Min Act: -0.0001

Data Index: 385284 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.7940. Min Act: -0.0000

Data Index: 867827 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.8197. Min Act: -0.0001

Data Index: 1108242 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 5.0309. Min Range: -5.0309

Max Act: 4.1188. Min Act: -0.0000

Data Index: 46695 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.8443. Min Act: -0.0000

Data Index: 868947 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.6598. Min Act: -0.0001

Data Index: 1141043 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.6197. Min Act: -0.0000

Data Index: 789871 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.7764. Min Act: -0.0000

Data Index: 530242 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.7517. Min Act: -0.0001

Data Index: 1138594 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.8452. Min Act: -0.0001

Data Index: 324713 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.6403. Min Act: -0.0000

Data Index: 207821 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.4807. Min Act: -0.0000

Data Index: 895648 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.4310. Min Act: -0.0001

Data Index: 1031902 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.5529. Min Act: -0.0000

Data Index: 1354975 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 5.0309. Min Range: -5.0309

Max Act: 3.5215. Min Act: -0.0000

Data Index: 579997 (C4 (Web Text))

Max Activating Token Index: 361