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

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

Neuron 1681 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: 2.3585. Min Range: -2.3585

Max Act: 2.3585. Min Act: -0.0001

Data Index: 1285609 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 2.3585. Min Range: -2.3585

Max Act: 2.2070. Min Act: -0.0000

Data Index: 146314 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 2.3585. Min Range: -2.3585

Max Act: 2.1503. Min Act: -0.0000

Data Index: 904097 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8807. Min Act: -0.0000

Data Index: 885649 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.9695. Min Act: -0.0000

Data Index: 83205 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.6127. Min Act: -0.0001

Data Index: 844427 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8425. Min Act: -0.0000

Data Index: 1018461 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.9263. Min Act: -0.0000

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8466. Min Act: -0.0001

Data Index: 200262 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1103884 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8536. Min Act: -0.0000

Data Index: 937664 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8433. Min Act: -0.0000

Data Index: 1066461 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8375. Min Act: -0.0000

Data Index: 326447 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8031. Min Act: -0.0000

Data Index: 363746 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8843. Min Act: -0.0000

Data Index: 650062 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.7806. Min Act: -0.0000

Data Index: 800245 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.6455. Min Act: -0.0000

Data Index: 473259 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.5642. Min Act: -0.0000

Data Index: 297418 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.8308. Min Act: -0.0000

Data Index: 879165 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 2.3585. Min Range: -2.3585

Max Act: 1.6308. Min Act: -0.0000

Data Index: 806903 (C4 (Web Text))

Max Activating Token Index: 805