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

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

Neuron 221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.8325. Min Act: -0.0000

Data Index: 542209 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7832. Min Act: -0.0000

Data Index: 844068 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7616. Min Act: -0.0000

Data Index: 1253472 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.6850. Min Act: -0.0000

Data Index: 886056 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.6871. Min Act: -0.0000

Data Index: 310368 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1259857 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.6372. Min Act: -0.0000

Data Index: 79123 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1356708 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5898. Min Act: -0.0000

Data Index: 346953 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5802. Min Act: -0.0000

Data Index: 685721 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5189. Min Act: -0.0000

Data Index: 519024 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5515. Min Act: -0.0000

Data Index: 421415 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.3691. Min Act: -0.0000

Data Index: 128230 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1350814 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1172523 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.5380. Min Act: -0.0000

Data Index: 1310989 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.4290. Min Act: -0.0000

Data Index: 57765 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.2640. Min Act: -0.0000

Data Index: 460084 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.3046. Min Act: -0.0000

Data Index: 603845 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.3711. Min Act: -0.0000

Data Index: 468650 (C4 (Web Text))

Max Activating Token Index: 297