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

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

Neuron 1490 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: 3.5339. Min Range: -3.5339

Max Act: 3.5339. Min Act: -0.0001

Data Index: 56356 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 3.5339. Min Range: -3.5339

Max Act: 3.1554. Min Act: -0.0001

Data Index: 1106633 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.8521. Min Act: -0.0001

Data Index: 317505 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.6057. Min Act: -0.0000

Data Index: 386962 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.5568. Min Act: -0.0001

Data Index: 488293 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.6714. Min Act: -0.0001

Data Index: 12976 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.4446. Min Act: -0.0001

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.3796. Min Act: -0.0000

Data Index: 444137 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.5512. Min Act: -0.0001

Data Index: 103162 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.4930. Min Act: -0.0000

Data Index: 85286 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.7585. Min Act: -0.0001

Data Index: 271646 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.4989. Min Act: -0.0000

Data Index: 1254323 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.5980. Min Act: -0.0001

Data Index: 437887 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.8628. Min Act: -0.0001

Data Index: 671130 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.5786. Min Act: -0.0001

Data Index: 307646 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.2097. Min Act: -0.0000

Data Index: 664402 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.6538. Min Act: -0.0001

Data Index: 90822 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.0696. Min Act: -0.0000

Data Index: 1283223 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.3837. Min Act: -0.0001

Data Index: 315963 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.5339. Min Range: -3.5339

Max Act: 2.4989. Min Act: -0.0000

Data Index: 1128195 (C4 (Web Text))

Max Activating Token Index: 74