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

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

Neuron 1192 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.8363. Min Act: -0.0001

Data Index: 93733 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.8465. Min Act: -0.0000

Data Index: 409150 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.8081. Min Act: -0.0001

Data Index: 906361 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.7016. Min Act: -0.0001

Data Index: 17877 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.7675. Min Act: -0.0001

Data Index: 388189 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.7157. Min Act: -0.0001

Data Index: 760366 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.7334. Min Act: -0.0001

Data Index: 854387 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6642. Min Act: -0.0000

Data Index: 399947 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6760. Min Act: -0.0000

Data Index: 815475 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6549. Min Act: -0.0001

Data Index: 749715 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6689. Min Act: -0.0001

Data Index: 850589 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6883. Min Act: -0.0001

Data Index: 429169 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6691. Min Act: -0.0001

Data Index: 7981 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6271. Min Act: -0.0001

Data Index: 551657 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6740. Min Act: -0.0001

Data Index: 944421 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6267. Min Act: -0.0001

Data Index: 492728 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5897. Min Act: -0.0001

Data Index: 616890 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6497. Min Act: -0.0001

Data Index: 826993 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6300. Min Act: -0.0000

Data Index: 375805 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5968. Min Act: -0.0001

Data Index: 372500 (C4 (Web Text))

Max Activating Token Index: 617