Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0001

Data Index: 946830 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0706. Min Act: -0.0001

Data Index: 484468 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0647. Min Act: -0.0001

Data Index: 51224 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1256544 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1153285 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0707. Min Act: -0.0001

Data Index: 210903 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1000470 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1228694 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0650. Min Act: -0.0001

Data Index: 488141 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0585. Min Act: -0.0001

Data Index: 373787 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0630. Min Act: -0.0001

Data Index: 46751 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0622. Min Act: -0.0001

Data Index: 841428 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1173778 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1287289 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0576. Min Act: -0.0001

Data Index: 670949 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0591. Min Act: -0.0001

Data Index: 256540 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0585. Min Act: -0.0001

Data Index: 884586 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0580. Min Act: -0.0001

Data Index: 352188 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0603. Min Act: -0.0001

Data Index: 563806 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0571. Min Act: -0.0001

Data Index: 844232 (C4 (Web Text))

Max Activating Token Index: 117