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

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

Neuron 5410 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: 3.3338. Min Range: -3.3338

Max Act: 3.1722. Min Act: -0.0001

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.0671. Min Act: -0.0001

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.3338. Min Act: -0.0001

Data Index: 597139 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.0705. Min Act: -0.0001

Data Index: 658704 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 3.3338. Min Range: -3.3338

Max Act: 3.0261. Min Act: -0.0001

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5863. Min Act: -0.0000

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.7815. Min Act: -0.0001

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5417. Min Act: -0.0000

Data Index: 569430 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5910. Min Act: -0.0000

Data Index: 1096290 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5894. Min Act: -0.0001

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.6916. Min Act: -0.0001

Data Index: 671881 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.8230. Min Act: -0.0000

Data Index: 764540 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5668. Min Act: -0.0001

Data Index: 575622 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5694. Min Act: -0.0001

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.3364. Min Act: -0.0001

Data Index: 883027 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5206. Min Act: -0.0001

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.5002. Min Act: -0.0000

Data Index: 200020 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.3706. Min Act: -0.0000

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.4597. Min Act: -0.0001

Data Index: 184789 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.3338. Min Range: -3.3338

Max Act: 2.3446. Min Act: -0.0001

Data Index: 1095811 (C4 (Web Text))

Max Activating Token Index: 187