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

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

Neuron 2385 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: 0.6471. Min Range: -0.6471

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1278663 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6034. Min Act: -0.0000

Data Index: 99980 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5770. Min Act: -0.0000

Data Index: 94344 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5699. Min Act: -0.0000

Data Index: 802104 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5389. Min Act: -0.0001

Data Index: 246931 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6330. Min Act: -0.0001

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1057029 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1082857 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5494. Min Act: -0.0000

Data Index: 958449 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5696. Min Act: -0.0000

Data Index: 801445 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1125434 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1130842 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5058. Min Act: -0.0000

Data Index: 367098 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1617442 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1075776 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5326. Min Act: -0.0000

Data Index: 219423 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1205527 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5289. Min Act: -0.0000

Data Index: 127463 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5068. Min Act: -0.0000

Data Index: 285126 (C4 (Web Text))

Max Activating Token Index: 42