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

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

Neuron 3287 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: 4.4865. Min Range: -4.4865

Max Act: 4.3165. Min Act: -0.0000

Data Index: 506390 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 4.4865. Min Range: -4.4865

Max Act: 4.4865. Min Act: -0.0000

Data Index: 1274883 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.8212. Min Act: -0.0000

Data Index: 1303835 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.7851. Min Act: -0.0000

Data Index: 1006345 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5882. Min Act: -0.0000

Data Index: 718982 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5336. Min Act: -0.0000

Data Index: 820754 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5370. Min Act: -0.0000

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5047. Min Act: -0.0000

Data Index: 409424 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.4523. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5861. Min Act: -0.0000

Data Index: 579528 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.3759. Min Act: -0.0000

Data Index: 867121 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.4956. Min Act: -0.0000

Data Index: 1028464 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.2072. Min Act: -0.0000

Data Index: 434691 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.5158. Min Act: -0.0000

Data Index: 243201 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.3319. Min Act: -0.0000

Data Index: 556445 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.4710. Min Act: -0.0000

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.3010. Min Act: -0.0000

Data Index: 74428 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.2869. Min Act: -0.0000

Data Index: 602113 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.0947. Min Act: -0.0000

Data Index: 27426 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 4.4865. Min Range: -4.4865

Max Act: 3.2350. Min Act: -0.0000

Data Index: 901005 (C4 (Web Text))

Max Activating Token Index: 14