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

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

Neuron 3682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2733. Min Act: -0.0000

Data Index: 563485 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2880. Min Act: -0.0000

Data Index: 988635 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2829. Min Act: -0.0000

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2359. Min Act: -0.0000

Data Index: 354408 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2637. Min Act: -0.0000

Data Index: 638661 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2616. Min Act: -0.0000

Data Index: 155508 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2508. Min Act: -0.0000

Data Index: 218705 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2590. Min Act: -0.0000

Data Index: 20436 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1000791 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2489. Min Act: -0.0000

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2384. Min Act: -0.0000

Data Index: 537841 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1211757 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1588397 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2298. Min Act: -0.0000

Data Index: 739113 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1479624 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2443. Min Act: -0.0000

Data Index: 52595 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1503601 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2164. Min Act: -0.0001

Data Index: 754670 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1412343 (Python Code)

Max Activating Token Index: 183