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

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

Neuron 5290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.3524. Min Act: -0.0002

Data Index: 134672 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.1917. Min Act: -0.0002

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.0134. Min Act: -0.0002

Data Index: 737396 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.9774. Min Act: -0.0002

Data Index: 365724 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.9070. Min Act: -0.0002

Data Index: 105771 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.9213. Min Act: -0.0002

Data Index: 52014 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.9086. Min Act: -0.0002

Data Index: 948313 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8589. Min Act: -0.0002

Data Index: 281381 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8602. Min Act: -0.0002

Data Index: 1352739 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8187. Min Act: -0.0002

Data Index: 422642 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8189. Min Act: -0.0002

Data Index: 356269 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7981. Min Act: -0.0002

Data Index: 1155428 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8052. Min Act: -0.0002

Data Index: 164909 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7977. Min Act: -0.0002

Data Index: 650462 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7987. Min Act: -0.0002

Data Index: 826211 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7935. Min Act: -0.0002

Data Index: 1278729 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7985. Min Act: -0.0002

Data Index: 935576 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8003. Min Act: -0.0003

Data Index: 1187411 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.8004. Min Act: -0.0002

Data Index: 15064 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.3524. Min Range: -1.3524

Max Act: 0.7910. Min Act: -0.0003

Data Index: 673223 (C4 (Web Text))

Max Activating Token Index: 189