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

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

Neuron 3491 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: 3.6000. Min Range: -3.6000

Max Act: 3.6000. Min Act: 0.0001

Data Index: 393217 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.6000. Min Range: -3.6000

Max Act: 3.1023. Min Act: -0.0000

Data Index: 1263003 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 3.6000. Min Range: -3.6000

Max Act: 3.0980. Min Act: 0.0000

Data Index: 772457 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 3.6000. Min Range: -3.6000

Max Act: 3.1037. Min Act: -0.0000

Data Index: 263072 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.8220. Min Act: -0.0000

Data Index: 1204685 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.8861. Min Act: -0.0000

Data Index: 416217 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.6792. Min Act: -0.0000

Data Index: 544196 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.4340. Min Act: -0.0000

Data Index: 261706 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.6734. Min Act: -0.0000

Data Index: 1162499 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.8156. Min Act: -0.0000

Data Index: 672311 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.5402. Min Act: -0.0000

Data Index: 337873 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.3638. Min Act: -0.0000

Data Index: 374223 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.4645. Min Act: -0.0000

Data Index: 1192414 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.3898. Min Act: -0.0000

Data Index: 711652 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.4878. Min Act: -0.0000

Data Index: 1310016 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.4529. Min Act: -0.0000

Data Index: 785132 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.4695. Min Act: -0.0000

Data Index: 95631 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1353609 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.2664. Min Act: -0.0000

Data Index: 422999 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.6000. Min Range: -3.6000

Max Act: 2.0982. Min Act: -0.0000

Data Index: 522703 (C4 (Web Text))

Max Activating Token Index: 700