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

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

Neuron 3552 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.9282. Min Act: -0.0003

Data Index: 756178 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7957. Min Act: -0.0003

Data Index: 22164 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7725. Min Act: -0.0003

Data Index: 835444 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6167. Min Act: -0.0003

Data Index: 174596 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7282. Min Act: -0.0003

Data Index: 1024967 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7666. Min Act: -0.0004

Data Index: 684066 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.8073. Min Act: -0.0003

Data Index: 990601 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6680. Min Act: -0.0003

Data Index: 273688 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7799. Min Act: -0.0003

Data Index: 765669 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7863. Min Act: -0.0003

Data Index: 245821 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6905. Min Act: -0.0003

Data Index: 476507 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7095. Min Act: -0.0003

Data Index: 1092959 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7325. Min Act: -0.0004

Data Index: 902539 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6803. Min Act: -0.0003

Data Index: 1101088 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.5983. Min Act: -0.0003

Data Index: 1241550 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7330. Min Act: -0.0003

Data Index: 1314645 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6687. Min Act: -0.0003

Data Index: 513848 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.6681. Min Act: -0.0003

Data Index: 1173211 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7383. Min Act: -0.0004

Data Index: 175918 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.9282. Min Range: -0.9282

Max Act: 0.7989. Min Act: -0.0003

Data Index: 1214334 (C4 (Web Text))

Max Activating Token Index: 749