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

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

Neuron 4824 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.8745. Min Act: -0.0001

Data Index: 1197196 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.8869. Min Act: -0.0000

Data Index: 178739 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.6035. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.6743. Min Act: -0.0000

Data Index: 713810 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.6251. Min Act: -0.0000

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.7403. Min Act: -0.0000

Data Index: 1178980 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.2278. Min Act: -0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.2441. Min Act: -0.0000

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.2206. Min Act: -0.0001

Data Index: 1145339 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 6.8869. Min Range: -6.8869

Max Act: 5.9629. Min Act: -0.0000

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.2981. Min Act: -0.0000

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 6.8869. Min Range: -6.8869

Max Act: 5.8646. Min Act: -0.0000

Data Index: 1255655 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 6.8869. Min Range: -6.8869

Max Act: 6.0278. Min Act: -0.0000

Data Index: 836947 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.9325. Min Act: -0.0000

Data Index: 1282764 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.6379. Min Act: -0.0000

Data Index: 536443 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.4538. Min Act: -0.0000

Data Index: 1228479 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.7302. Min Act: -0.0001

Data Index: 1221224 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.5359. Min Act: -0.0000

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.5036. Min Act: -0.0001

Data Index: 1011887 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 6.8869. Min Range: -6.8869

Max Act: 3.4133. Min Act: -0.0000

Data Index: 631911 (C4 (Web Text))

Max Activating Token Index: 907