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

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

Neuron 2238 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: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0000

Data Index: 774173 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5538. Min Act: -0.0000

Data Index: 87292 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1584140 (Python Code)

Max Activating Token Index: 151

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4700. Min Act: -0.0000

Data Index: 306234 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5616. Min Act: -0.0000

Data Index: 857385 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1008727 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4813. Min Act: -0.0000

Data Index: 426538 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1511403 (Python Code)

Max Activating Token Index: 863

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4901. Min Act: -0.0000

Data Index: 158442 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4993. Min Act: -0.0000

Data Index: 856562 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1044807 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1124822 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4455. Min Act: -0.0000

Data Index: 810677 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4692. Min Act: -0.0000

Data Index: 812001 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1551861 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4632. Min Act: -0.0000

Data Index: 533228 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1544021 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1413522 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1521144 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1327528 (C4 (Web Text))

Max Activating Token Index: 366