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

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

Neuron 645 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: 0.5106. Min Range: -0.5106

Max Act: 0.5106. Min Act: -0.0000

Data Index: 274863 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1467849 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1158565 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3792. Min Act: -0.0000

Data Index: 487871 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3353. Min Act: -0.0000

Data Index: 115260 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3588. Min Act: -0.0001

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3889. Min Act: -0.0000

Data Index: 55021 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3759. Min Act: -0.0000

Data Index: 374464 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3894. Min Act: -0.0000

Data Index: 215096 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3869. Min Act: -0.0000

Data Index: 158547 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3969. Min Act: -0.0000

Data Index: 297666 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1524053 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3662. Min Act: -0.0000

Data Index: 656332 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3444. Min Act: -0.0000

Data Index: 907327 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3730. Min Act: -0.0000

Data Index: 55343 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3842. Min Act: -0.0001

Data Index: 413604 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3593. Min Act: -0.0000

Data Index: 579034 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4079. Min Act: -0.0000

Data Index: 44497 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3705. Min Act: -0.0000

Data Index: 302252 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3496. Min Act: -0.0000

Data Index: 923285 (C4 (Web Text))

Max Activating Token Index: 124