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

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

Neuron 4474 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: 1.9782. Min Range: -1.9782

Max Act: 1.9782. Min Act: -0.0000

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2034. Min Act: -0.0000

Data Index: 717413 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.1882. Min Act: -0.0000

Data Index: 93147 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9661. Min Act: -0.0000

Data Index: 829425 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.0480. Min Act: -0.0000

Data Index: 778518 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.0225. Min Act: -0.0000

Data Index: 359552 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9579. Min Act: -0.0000

Data Index: 204448 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9288. Min Act: -0.0000

Data Index: 806669 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9274. Min Act: -0.0000

Data Index: 153667 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9681. Min Act: -0.0000

Data Index: 147235 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.8532. Min Act: -0.0000

Data Index: 798837 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.7380. Min Act: -0.0000

Data Index: 647345 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.8122. Min Act: -0.0000

Data Index: 748462 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.8532. Min Act: -0.0000

Data Index: 414274 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.7901. Min Act: -0.0000

Data Index: 439999 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.9244. Min Act: -0.0000

Data Index: 823257 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.7919. Min Act: -0.0000

Data Index: 956257 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.8076. Min Act: -0.0000

Data Index: 805032 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.9782. Min Range: -1.9782

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1054606 (C4 (Web Text))

Max Activating Token Index: 284