Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 307 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0003

Data Index: 102073 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0450. Min Act: -0.0003

Data Index: 782082 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0440. Min Act: -0.0003

Data Index: 224248 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0417. Min Act: -0.0003

Data Index: 580676 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1299349 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0380. Min Act: -0.0003

Data Index: 254356 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0383. Min Act: -0.0003

Data Index: 93961 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0389. Min Act: -0.0003

Data Index: 42309 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1126726 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1055697 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1031684 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0370. Min Act: -0.0003

Data Index: 487689 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0362. Min Act: -0.0003

Data Index: 174772 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1512527 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1213793 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1298010 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1576932 (Python Code)

Max Activating Token Index: 392

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0348. Min Act: -0.0003

Data Index: 428487 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0363. Min Act: -0.0003

Data Index: 620417 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0363. Min Act: -0.0003

Data Index: 138805 (C4 (Web Text))

Max Activating Token Index: 431