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

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

Neuron 4907 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: 4.0703. Min Range: -4.0703

Max Act: 4.0703. Min Act: -0.0000

Data Index: 43482 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 4.0703. Min Range: -4.0703

Max Act: 3.9559. Min Act: -0.0000

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 4.0703. Min Range: -4.0703

Max Act: 3.8823. Min Act: -0.0000

Data Index: 1290779 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.9782. Min Act: -0.0000

Data Index: 421081 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.9394. Min Act: -0.0000

Data Index: 308474 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.8934. Min Act: -0.0000

Data Index: 1331488 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.8732. Min Act: -0.0000

Data Index: 787316 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.6962. Min Act: -0.0000

Data Index: 778962 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 4.0703. Min Range: -4.0703

Max Act: 3.1370. Min Act: -0.0000

Data Index: 440553 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.6975. Min Act: -0.0000

Data Index: 1171476 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.5451. Min Act: -0.0000

Data Index: 388487 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.9307. Min Act: -0.0000

Data Index: 1319855 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.7772. Min Act: -0.0000

Data Index: 295748 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.8528. Min Act: -0.0000

Data Index: 1284984 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.7765. Min Act: -0.0000

Data Index: 526085 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.6103. Min Act: -0.0001

Data Index: 1267714 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.4948. Min Act: -0.0000

Data Index: 293242 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1276207 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.4306. Min Act: -0.0000

Data Index: 870336 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 4.0703. Min Range: -4.0703

Max Act: 2.5726. Min Act: -0.0000

Data Index: 160347 (C4 (Web Text))

Max Activating Token Index: 585