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

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

Neuron 3219 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: 1.5623. Min Range: -1.5623

Max Act: 1.5623. Min Act: -0.0000

Data Index: 707323 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.0643. Min Act: -0.0000

Data Index: 845843 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1212015 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1617784 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1028858 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1499434 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.1489. Min Act: -0.0000

Data Index: 134910 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.1202. Min Act: -0.0000

Data Index: 370203 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.0913. Min Act: -0.0000

Data Index: 616077 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1453799 (Python Code)

Max Activating Token Index: 813

Text #10

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1157166 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1228275 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.5623. Min Range: -1.5623

Max Act: 1.0018. Min Act: -0.0000

Data Index: 175197 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9930. Min Act: -0.0000

Data Index: 642181 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1023495 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9445. Min Act: -0.0000

Data Index: 206014 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9263. Min Act: -0.0000

Data Index: 862493 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.8643. Min Act: -0.0000

Data Index: 175556 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.9128. Min Act: -0.0000

Data Index: 698698 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.5623. Min Range: -1.5623

Max Act: 0.8411. Min Act: -0.0000

Data Index: 249534 (C4 (Web Text))

Max Activating Token Index: 411