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

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

Neuron 5056 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1068334 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8576. Min Act: -0.0000

Data Index: 317504 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.7872. Min Act: -0.0000

Data Index: 1203420 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.6317. Min Act: -0.0000

Data Index: 211551 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.5491. Min Act: -0.0000

Data Index: 561444 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.5379. Min Act: -0.0000

Data Index: 20455 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1052120 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4877. Min Act: -0.0000

Data Index: 257499 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4515. Min Act: -0.0000

Data Index: 257337 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1043122 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1351969 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1336406 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1226873 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4242. Min Act: -0.0000

Data Index: 699268 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4053. Min Act: -0.0000

Data Index: 1008024 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.3940. Min Act: -0.0000

Data Index: 403635 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4733. Min Act: -0.0000

Data Index: 1265276 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.3758. Min Act: -0.0000

Data Index: 756048 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1105005 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.4585. Min Act: -0.0000

Data Index: 969637 (C4 (Web Text))

Max Activating Token Index: 261