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

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

Neuron 6064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4482. Min Range: -2.4482

Max Act: 2.4482. Min Act: -0.0000

Data Index: 114154 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 2.4482. Min Range: -2.4482

Max Act: 2.3242. Min Act: -0.0000

Data Index: 660326 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.4482. Min Range: -2.4482

Max Act: 2.1894. Min Act: -0.0000

Data Index: 1000227 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 2.4482. Min Range: -2.4482

Max Act: 2.1241. Min Act: -0.0000

Data Index: 141334 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.9926. Min Act: -0.0000

Data Index: 8857 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.9949. Min Act: -0.0000

Data Index: 1050603 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.8528. Min Act: -0.0000

Data Index: 431591 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.6825. Min Act: -0.0000

Data Index: 730598 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.7722. Min Act: -0.0000

Data Index: 275793 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1221553 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.8356. Min Act: -0.0000

Data Index: 3737 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.7250. Min Act: -0.0000

Data Index: 1051138 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.7129. Min Act: -0.0000

Data Index: 916624 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1101572 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.4097. Min Act: -0.0000

Data Index: 875860 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.7786. Min Act: -0.0000

Data Index: 34189 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.5861. Min Act: -0.0000

Data Index: 747927 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.3408. Min Act: -0.0000

Data Index: 89509 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1268554 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 2.4482. Min Range: -2.4482

Max Act: 1.6670. Min Act: -0.0000

Data Index: 94084 (C4 (Web Text))

Max Activating Token Index: 625