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

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

Neuron 976 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: 1.4929. Min Range: -1.4929

Max Act: 1.4929. Min Act: -0.0001

Data Index: 149428 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1867. Min Act: -0.0001

Data Index: 588095 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3228. Min Act: -0.0001

Data Index: 1284792 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0571. Min Act: -0.0001

Data Index: 232762 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1725. Min Act: -0.0001

Data Index: 1325438 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.2425. Min Act: -0.0001

Data Index: 1336182 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1021. Min Act: -0.0000

Data Index: 707710 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1585. Min Act: -0.0001

Data Index: 693009 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0223. Min Act: -0.0001

Data Index: 702856 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1528. Min Act: -0.0001

Data Index: 375854 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0849. Min Act: -0.0001

Data Index: 861243 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.4929. Min Range: -1.4929

Max Act: 0.9997. Min Act: -0.0001

Data Index: 179605 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0289. Min Act: -0.0001

Data Index: 796992 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0210. Min Act: -0.0001

Data Index: 1244368 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.4929. Min Range: -1.4929

Max Act: 0.9526. Min Act: -0.0001

Data Index: 1123473 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0161. Min Act: -0.0001

Data Index: 761771 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0088. Min Act: -0.0001

Data Index: 65805 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0102. Min Act: -0.0001

Data Index: 1065437 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0080. Min Act: -0.0001

Data Index: 532057 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1320801 (C4 (Web Text))

Max Activating Token Index: 167