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

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

Neuron 4250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7484. Min Range: -2.7484

Max Act: 2.7484. Min Act: -0.0000

Data Index: 1238164 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 2.7484. Min Range: -2.7484

Max Act: 2.4041. Min Act: -0.0000

Data Index: 1060601 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.7484. Min Range: -2.7484

Max Act: 2.2034. Min Act: -0.0000

Data Index: 157869 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 2.7484. Min Range: -2.7484

Max Act: 2.2465. Min Act: -0.0000

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.9343. Min Act: -0.0000

Data Index: 804116 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.9323. Min Act: -0.0000

Data Index: 916158 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.9265. Min Act: -0.0000

Data Index: 218652 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.9111. Min Act: -0.0000

Data Index: 1201105 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.9616. Min Act: -0.0000

Data Index: 88628 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.8291. Min Act: -0.0000

Data Index: 1587755 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.8994. Min Act: -0.0000

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.7926. Min Act: -0.0000

Data Index: 1095357 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1248822 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.6500. Min Act: 0.0000

Data Index: 1102170 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.7134. Min Act: -0.0000

Data Index: 1449644 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.6905. Min Act: -0.0000

Data Index: 850771 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.6892. Min Act: -0.0000

Data Index: 919983 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1444953 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.7822. Min Act: -0.0000

Data Index: 1485396 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 2.7484. Min Range: -2.7484

Max Act: 1.6504. Min Act: -0.0000

Data Index: 622970 (C4 (Web Text))

Max Activating Token Index: 690