Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 121 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5502. Min Act: -0.0000

Data Index: 332746 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5439. Min Act: -0.0000

Data Index: 823063 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5034. Min Act: -0.0000

Data Index: 164083 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1001075 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4912. Min Act: -0.0000

Data Index: 392016 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1061994 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4481. Min Act: 0.0001

Data Index: 574497 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3945. Min Act: -0.0000

Data Index: 446956 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3830. Min Act: 0.0000

Data Index: 679358 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3712. Min Act: -0.0000

Data Index: 46161 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1347292 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3545. Min Act: -0.0000

Data Index: 414516 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3647. Min Act: 0.0000

Data Index: 707701 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3536. Min Act: -0.0000

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1610039 (Python Code)

Max Activating Token Index: 696

Text #15

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3430. Min Act: -0.0000

Data Index: 836228 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3492. Min Act: -0.0000

Data Index: 326248 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3309. Min Act: -0.0000

Data Index: 994369 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3299. Min Act: -0.0000

Data Index: 33744 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1153287 (C4 (Web Text))

Max Activating Token Index: 865