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

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

Neuron 61 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1295943 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2457. Min Act: -0.0000

Data Index: 921699 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2553. Min Act: -0.0000

Data Index: 808974 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2382. Min Act: -0.0000

Data Index: 885507 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2239. Min Act: -0.0000

Data Index: 77980 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1003145 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2211. Min Act: -0.0000

Data Index: 257322 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2138. Min Act: -0.0000

Data Index: 841536 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1589702 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1033175 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1567957 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2137. Min Act: -0.0000

Data Index: 85574 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2166. Min Act: -0.0000

Data Index: 629540 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1904. Min Act: -0.0000

Data Index: 237407 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1749. Min Act: -0.0000

Data Index: 620493 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1913. Min Act: -0.0000

Data Index: 500641 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1898. Min Act: -0.0000

Data Index: 501015 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1165219 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1604266 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1509167 (Python Code)

Max Activating Token Index: 264