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

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

Neuron 4601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3487. Min Range: -6.3487

Max Act: 6.3487. Min Act: -0.0000

Data Index: 593905 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.8401. Min Act: -0.0000

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.7653. Min Act: -0.0000

Data Index: 213490 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.5067. Min Act: -0.0000

Data Index: 74342 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.6217. Min Act: -0.0000

Data Index: 741726 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.1789. Min Act: -0.0000

Data Index: 1008358 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.5801. Min Act: -0.0000

Data Index: 394083 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.5065. Min Act: -0.0000

Data Index: 293830 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.3607. Min Act: -0.0000

Data Index: 2903 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 6.3487. Min Range: -6.3487

Max Act: 5.1513. Min Act: -0.0000

Data Index: 1035572 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.9401. Min Act: -0.0000

Data Index: 421258 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.6938. Min Act: -0.0000

Data Index: 808420 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.5360. Min Act: -0.0000

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.2797. Min Act: -0.0000

Data Index: 878532 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.3664. Min Act: -0.0000

Data Index: 145374 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.3681. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.1594. Min Act: -0.0000

Data Index: 990992 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.3071. Min Act: -0.0000

Data Index: 303201 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 6.3487. Min Range: -6.3487

Max Act: 4.1555. Min Act: -0.0000

Data Index: 1010387 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 6.3487. Min Range: -6.3487

Max Act: 3.9799. Min Act: -0.0000

Data Index: 841698 (C4 (Web Text))

Max Activating Token Index: 326