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

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

Neuron 2518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7685. Min Act: -0.0000

Data Index: 357381 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.8189. Min Act: -0.0000

Data Index: 91390 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4555. Min Act: -0.0000

Data Index: 31302 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.3480. Min Act: -0.0000

Data Index: 1311273 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4841. Min Act: -0.0000

Data Index: 948939 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4682. Min Act: -0.0000

Data Index: 382231 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.3944. Min Act: -0.0000

Data Index: 1171217 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.3476. Min Act: -0.0000

Data Index: 134331 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.3252. Min Act: -0.0000

Data Index: 876904 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.1762. Min Act: -0.0000

Data Index: 388837 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.1693. Min Act: -0.0000

Data Index: 93388 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.2644. Min Act: -0.0000

Data Index: 1005994 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.2591. Min Act: -0.0000

Data Index: 54983 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.2104. Min Act: -0.0000

Data Index: 897245 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.3322. Min Act: -0.0000

Data Index: 367896 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4830. Min Act: -0.0000

Data Index: 364097 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.2948. Min Act: -0.0000

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.2804. Min Act: -0.0000

Data Index: 548995 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.0985. Min Act: -0.0000

Data Index: 1125858 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.8189. Min Range: -3.8189

Max Act: 2.8510. Min Act: -0.0000

Data Index: 55699 (C4 (Web Text))

Max Activating Token Index: 298