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

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

Neuron 4470 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.7560. Min Act: -0.0000

Data Index: 1055982 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1026956 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.6079. Min Act: -0.0000

Data Index: 937106 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.6049. Min Act: -0.0000

Data Index: 249266 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.4292. Min Act: -0.0000

Data Index: 229554 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.4495. Min Act: -0.0000

Data Index: 1010918 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1287193 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.3095. Min Act: -0.0000

Data Index: 158891 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1268882 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.2067. Min Act: -0.0000

Data Index: 901120 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.3163. Min Act: -0.0000

Data Index: 624966 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.2387. Min Act: -0.0000

Data Index: 670670 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1323659 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.2644. Min Act: -0.0000

Data Index: 609097 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1262514 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.1529. Min Act: -0.0000

Data Index: 789288 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.1494. Min Act: -0.0000

Data Index: 190832 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.2027. Min Act: -0.0000

Data Index: 468216 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.7560. Min Range: -1.7560

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1318665 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.7560. Min Range: -1.7560

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1063943 (C4 (Web Text))

Max Activating Token Index: 652