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

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

Neuron 3815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1124. Min Range: -3.1124

Max Act: 3.1124. Min Act: -0.0000

Data Index: 1383448 (Python Code)

Max Activating Token Index: 871

Text #1

Max Range: 3.1124. Min Range: -3.1124

Max Act: 3.0423. Min Act: -0.0000

Data Index: 513057 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.8289. Min Act: -0.0000

Data Index: 152959 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.8340. Min Act: -0.0000

Data Index: 930196 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.6649. Min Act: -0.0000

Data Index: 113721 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.4780. Min Act: -0.0000

Data Index: 1162358 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.6815. Min Act: -0.0000

Data Index: 715250 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.5038. Min Act: -0.0000

Data Index: 894888 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.5049. Min Act: -0.0000

Data Index: 173482 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.6118. Min Act: -0.0000

Data Index: 591625 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.4796. Min Act: -0.0000

Data Index: 370522 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.4740. Min Act: -0.0000

Data Index: 1273127 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.5616. Min Act: -0.0000

Data Index: 279270 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.4410. Min Act: -0.0000

Data Index: 988475 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.4319. Min Act: -0.0000

Data Index: 2777 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.6330. Min Act: -0.0000

Data Index: 860853 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.3667. Min Act: -0.0000

Data Index: 328929 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.3562. Min Act: -0.0000

Data Index: 300628 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.2318. Min Act: -0.0000

Data Index: 603845 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 3.1124. Min Range: -3.1124

Max Act: 2.3236. Min Act: -0.0000

Data Index: 196071 (C4 (Web Text))

Max Activating Token Index: 63