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

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

Neuron 2295 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.1058. Min Act: -0.0001

Data Index: 240737 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.6014. Min Act: -0.0001

Data Index: 1031274 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.2824. Min Act: -0.0001

Data Index: 406810 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4229. Min Act: -0.0001

Data Index: 325859 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.0753. Min Act: -0.0001

Data Index: 1317978 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.1741. Min Act: -0.0001

Data Index: 837224 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9039. Min Act: -0.0001

Data Index: 190548 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9038. Min Act: -0.0001

Data Index: 1256270 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.2678. Min Act: -0.0001

Data Index: 162594 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.7606. Min Act: -0.0001

Data Index: 875060 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4053. Min Act: -0.0001

Data Index: 786276 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9949. Min Act: -0.0001

Data Index: 148001 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.1229. Min Act: -0.0001

Data Index: 25997 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.5308. Min Act: -0.0001

Data Index: 465303 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.2531. Min Act: -0.0001

Data Index: 1347428 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.8480. Min Act: -0.0001

Data Index: 151373 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9387. Min Act: -0.0001

Data Index: 1237204 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.0918. Min Act: -0.0001

Data Index: 1287926 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.9712. Min Act: -0.0001

Data Index: 514680 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.6014. Min Range: -3.6014

Max Act: 2.8275. Min Act: -0.0001

Data Index: 495280 (C4 (Web Text))

Max Activating Token Index: 922