Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6425. Min Act: -0.0001

Data Index: 507286 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6294. Min Act: -0.0001

Data Index: 1343865 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.7359. Min Act: -0.0001

Data Index: 1197063 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6045. Min Act: -0.0001

Data Index: 991011 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.7881. Min Act: -0.0001

Data Index: 857824 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5534. Min Act: -0.0001

Data Index: 284567 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6792. Min Act: -0.0001

Data Index: 1274833 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5114. Min Act: -0.0001

Data Index: 1174824 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6437. Min Act: -0.0001

Data Index: 1306652 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5622. Min Act: -0.0001

Data Index: 1164241 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6339. Min Act: -0.0001

Data Index: 392884 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5412. Min Act: -0.0001

Data Index: 235841 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6518. Min Act: -0.0001

Data Index: 140632 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5635. Min Act: -0.0001

Data Index: 1143232 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5145. Min Act: -0.0001

Data Index: 639205 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6622. Min Act: -0.0001

Data Index: 16201 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5504. Min Act: -0.0001

Data Index: 81843 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5041. Min Act: -0.0001

Data Index: 1125456 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6263. Min Act: -0.0001

Data Index: 738974 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5268. Min Act: -0.0001

Data Index: 267941 (C4 (Web Text))

Max Activating Token Index: 731