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

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

Neuron 5975 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: 2.3154. Min Range: -2.3154

Max Act: 2.3154. Min Act: -0.0000

Data Index: 161853 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 2.3154. Min Range: -2.3154

Max Act: 2.0389. Min Act: -0.0000

Data Index: 1211801 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 2.3154. Min Range: -2.3154

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1653369 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.9766. Min Act: -0.0000

Data Index: 1459202 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 2.3154. Min Range: -2.3154

Max Act: 2.1747. Min Act: -0.0000

Data Index: 534314 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.3154. Min Range: -2.3154

Max Act: 2.1460. Min Act: -0.0000

Data Index: 835901 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 2.3154. Min Range: -2.3154

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1103595 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8975. Min Act: -0.0000

Data Index: 367216 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1025689 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8447. Min Act: -0.0000

Data Index: 798103 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8471. Min Act: -0.0000

Data Index: 1128619 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8416. Min Act: -0.0000

Data Index: 183781 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.9135. Min Act: -0.0000

Data Index: 235849 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.9208. Min Act: -0.0000

Data Index: 1554199 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.7787. Min Act: -0.0000

Data Index: 435611 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1187832 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8204. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1032756 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.9002. Min Act: -0.0000

Data Index: 601991 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 2.3154. Min Range: -2.3154

Max Act: 1.7095. Min Act: -0.0000

Data Index: 751288 (C4 (Web Text))

Max Activating Token Index: 862