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

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

Neuron 1991 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: 0.6233. Min Range: -0.6233

Max Act: 0.6233. Min Act: -0.0000

Data Index: 949224 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5876. Min Act: -0.0000

Data Index: 264553 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.6197. Min Act: -0.0000

Data Index: 840678 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1069340 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1331464 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5918. Min Act: -0.0000

Data Index: 288587 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5800. Min Act: -0.0000

Data Index: 80643 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5591. Min Act: -0.0000

Data Index: 846800 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5574. Min Act: -0.0000

Data Index: 281941 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1262962 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5649. Min Act: -0.0000

Data Index: 659326 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5652. Min Act: -0.0000

Data Index: 662031 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1098372 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1053412 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5267. Min Act: -0.0000

Data Index: 404687 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5231. Min Act: 0.0000

Data Index: 953663 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1195723 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5155. Min Act: -0.0000

Data Index: 906675 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1068110 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1207997 (C4 (Web Text))

Max Activating Token Index: 965