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

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

Neuron 899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6323. Min Act: -0.0000

Data Index: 472651 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5508. Min Act: -0.0000

Data Index: 23947 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1048695 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4728. Min Act: -0.0000

Data Index: 335219 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4922. Min Act: -0.0000

Data Index: 134306 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5240. Min Act: -0.0000

Data Index: 886462 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4586. Min Act: -0.0000

Data Index: 315 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4967. Min Act: -0.0000

Data Index: 875774 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1276567 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4880. Min Act: -0.0000

Data Index: 603274 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1196674 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4398. Min Act: -0.0000

Data Index: 454839 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4616. Min Act: -0.0000

Data Index: 779589 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4252. Min Act: -0.0000

Data Index: 975723 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1297175 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4150. Min Act: -0.0000

Data Index: 787070 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4128. Min Act: -0.0000

Data Index: 874388 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4100. Min Act: -0.0000

Data Index: 287090 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1097782 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.3942. Min Act: -0.0000

Data Index: 317955 (C4 (Web Text))

Max Activating Token Index: 392