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

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

Neuron 1765 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1261105 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4095. Min Act: -0.0001

Data Index: 341724 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3343. Min Act: -0.0001

Data Index: 745466 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2780. Min Act: -0.0001

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1287252 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2792. Min Act: -0.0001

Data Index: 44622 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2853. Min Act: -0.0001

Data Index: 204513 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1332206 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2943. Min Act: -0.0001

Data Index: 66620 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2767. Min Act: -0.0001

Data Index: 364294 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2470. Min Act: -0.0001

Data Index: 302715 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2388. Min Act: -0.0001

Data Index: 628064 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1022425 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2354. Min Act: -0.0001

Data Index: 955021 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2323. Min Act: -0.0001

Data Index: 288760 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2233. Min Act: -0.0001

Data Index: 965706 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2348. Min Act: -0.0001

Data Index: 285226 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1356449 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2318. Min Act: -0.0001

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.2119. Min Act: -0.0001

Data Index: 624115 (C4 (Web Text))

Max Activating Token Index: 431