Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3789 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0000

Data Index: 41211 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2093. Min Act: -0.0000

Data Index: 217037 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2404. Min Act: -0.0000

Data Index: 456792 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2096. Min Act: -0.0000

Data Index: 807912 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2105. Min Act: -0.0000

Data Index: 334269 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1793. Min Act: -0.0000

Data Index: 282905 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1601. Min Act: -0.0000

Data Index: 88160 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1202355 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1956. Min Act: -0.0000

Data Index: 324751 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1231710 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1526. Min Act: -0.0000

Data Index: 463232 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1499. Min Act: -0.0000

Data Index: 438381 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1582. Min Act: -0.0000

Data Index: 406842 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1652. Min Act: -0.0000

Data Index: 834473 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1063496 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1396. Min Act: -0.0000

Data Index: 870831 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1143. Min Act: -0.0000

Data Index: 188362 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1070085 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1535. Min Act: -0.0000

Data Index: 454146 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.1274. Min Act: -0.0000

Data Index: 440950 (C4 (Web Text))

Max Activating Token Index: 75