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

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

Neuron 5633 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5906. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5314. Min Act: -0.0000

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4661. Min Act: -0.0000

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1613843 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5234. Min Act: -0.0000

Data Index: 792918 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1216747 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4622. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1315796 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4309. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4458. Min Act: -0.0000

Data Index: 411604 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4306. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1368879 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1095535 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4117. Min Act: -0.0000

Data Index: 100137 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1514603 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3699. Min Act: -0.0000

Data Index: 417544 (C4 (Web Text))

Max Activating Token Index: 715