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

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

Neuron 4904 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0402. Min Range: -1.0402

Max Act: 1.0402. Min Act: -0.0001

Data Index: 1084141 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.9920. Min Act: -0.0001

Data Index: 645513 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.8108. Min Act: -0.0001

Data Index: 947842 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1293006 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.8123. Min Act: -0.0000

Data Index: 607348 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7183. Min Act: -0.0001

Data Index: 337144 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6986. Min Act: -0.0001

Data Index: 622161 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7688. Min Act: -0.0001

Data Index: 597430 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7159. Min Act: -0.0001

Data Index: 582252 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1062165 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7049. Min Act: -0.0001

Data Index: 923588 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7603. Min Act: -0.0001

Data Index: 145044 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1216165 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6847. Min Act: -0.0001

Data Index: 766614 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6359. Min Act: -0.0001

Data Index: 246184 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6597. Min Act: -0.0001

Data Index: 912494 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6630. Min Act: -0.0001

Data Index: 960742 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6803. Min Act: -0.0001

Data Index: 1102220 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6959. Min Act: -0.0001

Data Index: 233967 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.0402. Min Range: -1.0402

Max Act: 0.6199. Min Act: -0.0001

Data Index: 256386 (C4 (Web Text))

Max Activating Token Index: 682