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

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

Neuron 5745 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1006. Min Range: -2.1006

Max Act: 2.1006. Min Act: -0.0000

Data Index: 211704 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.6078. Min Act: -0.0000

Data Index: 614601 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.5710. Min Act: -0.0000

Data Index: 161041 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.6300. Min Act: -0.0000

Data Index: 918894 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1281118 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.5509. Min Act: -0.0000

Data Index: 722236 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.5495. Min Act: -0.0000

Data Index: 184926 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4585. Min Act: -0.0000

Data Index: 60951 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4466. Min Act: -0.0000

Data Index: 549253 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4785. Min Act: -0.0000

Data Index: 509251 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4637. Min Act: -0.0000

Data Index: 457070 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4343. Min Act: -0.0000

Data Index: 27786 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.5183. Min Act: 0.0000

Data Index: 299738 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4214. Min Act: -0.0000

Data Index: 957632 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4572. Min Act: 0.0000

Data Index: 918728 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2538. Min Act: -0.0000

Data Index: 782181 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.3158. Min Act: -0.0000

Data Index: 931088 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.3051. Min Act: -0.0000

Data Index: 931827 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2802. Min Act: -0.0000

Data Index: 444141 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2971. Min Act: 0.0000

Data Index: 627209 (C4 (Web Text))

Max Activating Token Index: 525