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

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

Neuron 3874 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: 1.0479. Min Range: -1.0479

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.0479. Min Range: -1.0479

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1257 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9131. Min Act: -0.0001

Data Index: 805056 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8429. Min Act: -0.0001

Data Index: 1200594 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7459. Min Act: -0.0001

Data Index: 86659 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7911. Min Act: -0.0001

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7856. Min Act: -0.0001

Data Index: 857924 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7741. Min Act: -0.0001

Data Index: 3060 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7396. Min Act: -0.0001

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6965. Min Act: -0.0001

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7749. Min Act: -0.0001

Data Index: 945782 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8200. Min Act: -0.0001

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7313. Min Act: -0.0001

Data Index: 425121 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6749. Min Act: -0.0001

Data Index: 1302532 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6918. Min Act: -0.0001

Data Index: 971194 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7003. Min Act: -0.0001

Data Index: 110599 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.7202. Min Act: -0.0001

Data Index: 61055 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6405. Min Act: -0.0001

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.6489. Min Act: -0.0001

Data Index: 91540 (C4 (Web Text))

Max Activating Token Index: 756