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

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

Neuron 5394 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: 2.6688. Min Range: -2.6688

Max Act: 2.6688. Min Act: -0.0000

Data Index: 694052 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.6380. Min Act: -0.0000

Data Index: 1210132 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.6095. Min Act: -0.0000

Data Index: 566279 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.5613. Min Act: -0.0000

Data Index: 945071 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.5155. Min Act: -0.0000

Data Index: 488688 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.6634. Min Act: -0.0000

Data Index: 690733 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.4994. Min Act: -0.0000

Data Index: 1170366 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.4216. Min Act: -0.0000

Data Index: 543507 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.3964. Min Act: -0.0000

Data Index: 1257677 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1125. Min Act: -0.0000

Data Index: 821290 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.4395. Min Act: -0.0000

Data Index: 648509 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.3019. Min Act: -0.0000

Data Index: 185054 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1647. Min Act: -0.0000

Data Index: 146335 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.2359. Min Act: -0.0000

Data Index: 1356583 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.2958. Min Act: -0.0000

Data Index: 1649839 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.0700. Min Act: -0.0000

Data Index: 157711 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1556. Min Act: -0.0000

Data Index: 115382 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1421. Min Act: -0.0000

Data Index: 602239 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1313. Min Act: -0.0000

Data Index: 593135 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 2.6688. Min Range: -2.6688

Max Act: 2.1053. Min Act: -0.0000

Data Index: 886993 (C4 (Web Text))

Max Activating Token Index: 97