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

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

Neuron 329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1646478 (Python Code)

Max Activating Token Index: 685

Text #1

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3057. Min Act: -0.0001

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1138198 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2757. Min Act: -0.0001

Data Index: 579537 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2756. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1484444 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2714. Min Act: -0.0001

Data Index: 898099 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2710. Min Act: -0.0001

Data Index: 1477795 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2599. Min Act: -0.0000

Data Index: 247362 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2461. Min Act: -0.0000

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1544007 (Python Code)

Max Activating Token Index: 429

Text #11

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1466425 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2397. Min Act: -0.0001

Data Index: 188015 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2376. Min Act: -0.0000

Data Index: 653941 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1611709 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2408. Min Act: -0.0001

Data Index: 917693 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1080411 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1008646 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1493876 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2503. Min Act: -0.0000

Data Index: 314795 (C4 (Web Text))

Max Activating Token Index: 221