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

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

Neuron 3070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3372. Min Act: -0.0000

Data Index: 573425 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3796. Min Act: -0.0001

Data Index: 1440734 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1741. Min Act: -0.0000

Data Index: 292652 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1104. Min Act: -0.0000

Data Index: 620965 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.0407. Min Act: -0.0000

Data Index: 538444 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9778. Min Act: -0.0000

Data Index: 974010 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9537. Min Act: -0.0000

Data Index: 946254 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1181474 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1225875 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1252970 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8446. Min Act: -0.0000

Data Index: 442389 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8779. Min Act: -0.0000

Data Index: 909548 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8535. Min Act: -0.0000

Data Index: 930362 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1109229 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8325. Min Act: -0.0000

Data Index: 505904 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8352. Min Act: -0.0001

Data Index: 263519 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1358671 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8457. Min Act: -0.0000

Data Index: 573729 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1107331 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.7789. Min Act: -0.0000

Data Index: 753868 (C4 (Web Text))

Max Activating Token Index: 783