Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2481. Min Range: -1.2481

Max Act: 1.2481. Min Act: -0.0000

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.2481. Min Range: -1.2481

Max Act: 1.0706. Min Act: -0.0000

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.2481. Min Range: -1.2481

Max Act: 1.0099. Min Act: -0.0000

Data Index: 969249 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.9976. Min Act: 0.0000

Data Index: 940255 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8590. Min Act: -0.0000

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8270. Min Act: -0.0000

Data Index: 657491 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8451. Min Act: -0.0000

Data Index: 837718 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8337. Min Act: -0.0000

Data Index: 668728 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7249. Min Act: -0.0000

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8645. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7885. Min Act: -0.0000

Data Index: 958269 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8126. Min Act: -0.0000

Data Index: 669461 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7752. Min Act: 0.0000

Data Index: 243375 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7973. Min Act: -0.0000

Data Index: 947258 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7725. Min Act: -0.0000

Data Index: 555193 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.8247. Min Act: -0.0000

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7354. Min Act: -0.0000

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1227633 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.2481. Min Range: -1.2481

Max Act: 0.7855. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 587