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

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

Neuron 4290 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.5742. Min Act: -0.0000

Data Index: 1064706 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.0889. Min Act: -0.0000

Data Index: 95423 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.5742. Min Range: -3.5742

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1366023 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.9407. Min Act: -0.0000

Data Index: 4532 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.3476. Min Act: -0.0000

Data Index: 743848 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.4835. Min Act: -0.0001

Data Index: 522647 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.6789. Min Act: -0.0000

Data Index: 1540758 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.5397. Min Act: -0.0000

Data Index: 1433136 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.6754. Min Act: -0.0000

Data Index: 1026054 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.5174. Min Act: -0.0000

Data Index: 1177459 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.7296. Min Act: -0.0000

Data Index: 1484789 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.4625. Min Act: -0.0000

Data Index: 866937 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.3309. Min Act: -0.0000

Data Index: 536903 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1248890 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1367240 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.2992. Min Act: -0.0000

Data Index: 245248 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.0868. Min Act: -0.0000

Data Index: 1334485 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.5041. Min Act: -0.0000

Data Index: 311789 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.2737. Min Act: -0.0001

Data Index: 1176110 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.2764. Min Act: -0.0001

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 236