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

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

Neuron 3906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.6234. Min Act: -0.0001

Data Index: 288286 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.7687. Min Act: -0.0001

Data Index: 528514 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.6785. Min Act: -0.0001

Data Index: 227889 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.4049. Min Act: -0.0001

Data Index: 564963 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.7051. Min Act: -0.0001

Data Index: 287922 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.0764. Min Act: -0.0001

Data Index: 1317518 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.1966. Min Act: -0.0001

Data Index: 537257 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.5351. Min Act: -0.0001

Data Index: 999416 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.6052. Min Act: -0.0001

Data Index: 224327 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.8283. Min Act: -0.0001

Data Index: 651430 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.8584. Min Act: -0.0001

Data Index: 94451 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 4.7687. Min Range: -4.7687

Max Act: 4.1281. Min Act: -0.0001

Data Index: 671663 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.6694. Min Act: -0.0001

Data Index: 593889 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.7060. Min Act: -0.0001

Data Index: 1289354 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.5402. Min Act: -0.0001

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.6842. Min Act: -0.0001

Data Index: 1353571 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.2283. Min Act: -0.0001

Data Index: 741409 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.2779. Min Act: -0.0001

Data Index: 28707 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.2811. Min Act: -0.0001

Data Index: 526719 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 4.7687. Min Range: -4.7687

Max Act: 3.2525. Min Act: -0.0001

Data Index: 1202405 (C4 (Web Text))

Max Activating Token Index: 593