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

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

Neuron 3286 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9401. Min Act: -0.0001

Data Index: 1477796 (Python Code)

Max Activating Token Index: 750

Text #1

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8216. Min Act: -0.0001

Data Index: 1498311 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1579295 (Python Code)

Max Activating Token Index: 750

Text #3

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1437213 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1641162 (Python Code)

Max Activating Token Index: 521

Text #5

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1461924 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1403131 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1435799 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6572. Min Act: -0.0001

Data Index: 1618807 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1525781 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6055. Min Act: -0.0001

Data Index: 1618950 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1602929 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6270. Min Act: -0.0001

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1532264 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1151718 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6188. Min Act: -0.0001

Data Index: 706834 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1573516 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1606123 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.5975. Min Act: -0.0000

Data Index: 447252 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1615188 (Python Code)

Max Activating Token Index: 925