Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.6041. Min Act: -0.0002

Data Index: 1168772 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.2474. Min Act: -0.0002

Data Index: 1129568 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.2386. Min Act: -0.0001

Data Index: 408183 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.2961. Min Act: -0.0001

Data Index: 649801 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0294. Min Act: -0.0001

Data Index: 819728 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0124. Min Act: -0.0002

Data Index: 948980 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0565. Min Act: -0.0001

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0451. Min Act: -0.0001

Data Index: 8696 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0502. Min Act: -0.0001

Data Index: 1108134 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.1076. Min Act: -0.0001

Data Index: 1538401 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.1373. Min Act: -0.0002

Data Index: 645251 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0559. Min Act: -0.0002

Data Index: 1177339 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0161. Min Act: -0.0002

Data Index: 542305 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.1259. Min Act: -0.0001

Data Index: 631963 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0638. Min Act: -0.0001

Data Index: 405137 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0474. Min Act: -0.0002

Data Index: 186670 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0540. Min Act: -0.0001

Data Index: 388326 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0698. Min Act: -0.0002

Data Index: 118494 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.6041. Min Range: -1.6041

Max Act: 0.9216. Min Act: -0.0002

Data Index: 100233 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.0281. Min Act: -0.0002

Data Index: 306487 (C4 (Web Text))

Max Activating Token Index: 891