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

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

Neuron 453 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2938. Min Range: -4.2938

Max Act: 4.2938. Min Act: -0.0000

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 4.2938. Min Range: -4.2938

Max Act: 3.3046. Min Act: -0.0000

Data Index: 125962 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.3526. Min Act: -0.0000

Data Index: 1026616 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.5522. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.2255. Min Act: -0.0000

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.1973. Min Act: -0.0000

Data Index: 1045426 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.0562. Min Act: -0.0000

Data Index: 789627 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.9613. Min Act: -0.0000

Data Index: 88189 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1510395 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.8350. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.9860. Min Act: -0.0000

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.7821. Min Act: -0.0000

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.8953. Min Act: -0.0000

Data Index: 260517 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 4.2938. Min Range: -4.2938

Max Act: 2.0651. Min Act: -0.0000

Data Index: 561626 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.7232. Min Act: -0.0000

Data Index: 480402 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.8229. Min Act: -0.0000

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.6898. Min Act: -0.0000

Data Index: 477059 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.6827. Min Act: -0.0000

Data Index: 1090750 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.7768. Min Act: -0.0000

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 4.2938. Min Range: -4.2938

Max Act: 1.9740. Min Act: -0.0000

Data Index: 1149638 (C4 (Web Text))

Max Activating Token Index: 234