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

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

Neuron 4966 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: 2.6955. Min Range: -2.6955

Max Act: 2.6955. Min Act: -0.0000

Data Index: 250544 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.5465. Min Act: -0.0000

Data Index: 495535 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.5513. Min Act: -0.0000

Data Index: 1273114 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.2386. Min Act: -0.0000

Data Index: 460238 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1344411 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.3138. Min Act: -0.0000

Data Index: 666315 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.2715. Min Act: -0.0000

Data Index: 101131 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.2494. Min Act: -0.0000

Data Index: 253759 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1108. Min Act: -0.0000

Data Index: 668735 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1872. Min Act: -0.0000

Data Index: 1357655 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.2616. Min Act: -0.0000

Data Index: 830322 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1534. Min Act: -0.0000

Data Index: 521214 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1324. Min Act: -0.0000

Data Index: 915645 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1152. Min Act: -0.0000

Data Index: 368456 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.0815. Min Act: -0.0000

Data Index: 214782 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 2.6955. Min Range: -2.6955

Max Act: 1.9770. Min Act: -0.0000

Data Index: 224547 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.0879. Min Act: -0.0000

Data Index: 714930 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.6955. Min Range: -2.6955

Max Act: 1.9653. Min Act: -0.0000

Data Index: 494682 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.1749. Min Act: -0.0000

Data Index: 853429 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 2.6955. Min Range: -2.6955

Max Act: 2.0682. Min Act: -0.0000

Data Index: 1011797 (C4 (Web Text))

Max Activating Token Index: 3