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

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

Neuron 4977 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: 3.7676. Min Range: -3.7676

Max Act: 3.7676. Min Act: -0.0000

Data Index: 146367 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 3.7676. Min Range: -3.7676

Max Act: 3.0632. Min Act: -0.0000

Data Index: 1082576 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.6499. Min Act: -0.0000

Data Index: 81379 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.8441. Min Act: -0.0000

Data Index: 38522 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.9533. Min Act: -0.0000

Data Index: 1088110 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.7878. Min Act: -0.0000

Data Index: 646440 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.7664. Min Act: -0.0000

Data Index: 1268533 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.6589. Min Act: -0.0000

Data Index: 999324 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.6502. Min Act: -0.0000

Data Index: 1278325 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.5454. Min Act: -0.0000

Data Index: 200037 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.5377. Min Act: -0.0000

Data Index: 1081109 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.3937. Min Act: -0.0000

Data Index: 615241 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.5264. Min Act: -0.0000

Data Index: 784722 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.6280. Min Act: -0.0000

Data Index: 1091876 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1400835 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1394993 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.6226. Min Act: -0.0000

Data Index: 595612 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1102147 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.2456. Min Act: -0.0000

Data Index: 7393 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.7676. Min Range: -3.7676

Max Act: 2.2617. Min Act: -0.0000

Data Index: 809262 (C4 (Web Text))

Max Activating Token Index: 800