Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.3155. Min Act: -0.0003

Data Index: 1582411 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9531. Min Act: -0.0004

Data Index: 1632301 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2236. Min Act: -0.0003

Data Index: 1486502 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.8334. Min Act: -0.0003

Data Index: 1536866 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1445. Min Act: -0.0003

Data Index: 1610877 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1348. Min Act: -0.0004

Data Index: 1533918 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1824. Min Act: -0.0003

Data Index: 1556312 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9253. Min Act: -0.0003

Data Index: 1562494 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9537. Min Act: -0.0004

Data Index: 1543767 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0749. Min Act: -0.0003

Data Index: 1535062 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1724. Min Act: -0.0003

Data Index: 1530612 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1422. Min Act: -0.0003

Data Index: 1430214 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0650. Min Act: -0.0003

Data Index: 1548508 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9414. Min Act: -0.0004

Data Index: 1378547 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.8319. Min Act: -0.0003

Data Index: 1559666 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9394. Min Act: -0.0003

Data Index: 1386341 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1203. Min Act: -0.0003

Data Index: 1371997 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0125. Min Act: -0.0003

Data Index: 1510031 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0397. Min Act: -0.0003

Data Index: 1543394 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9205. Min Act: -0.0003

Data Index: 1399793 (Python Code)

Max Activating Token Index: 973