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

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

Neuron 4402 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: 3.6068. Min Range: -3.6068

Max Act: 3.6068. Min Act: -0.0000

Data Index: 85584 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.5646. Min Act: -0.0001

Data Index: 821457 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.4321. Min Act: -0.0000

Data Index: 277344 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.4051. Min Act: -0.0000

Data Index: 321203 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.3436. Min Act: -0.0001

Data Index: 525438 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.2025. Min Act: -0.0000

Data Index: 678041 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.2992. Min Act: -0.0000

Data Index: 984807 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1105. Min Act: -0.0000

Data Index: 81320 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.2379. Min Act: -0.0000

Data Index: 1202820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1650. Min Act: -0.0001

Data Index: 1345375 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.3265. Min Act: -0.0000

Data Index: 808353 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1439. Min Act: -0.0001

Data Index: 64521 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1540. Min Act: -0.0000

Data Index: 471450 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1500. Min Act: -0.0000

Data Index: 924560 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.1286. Min Act: -0.0001

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.2605. Min Act: -0.0000

Data Index: 4568 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.6068. Min Range: -3.6068

Max Act: 2.9523. Min Act: -0.0000

Data Index: 1019876 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.2446. Min Act: -0.0000

Data Index: 490974 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.6068. Min Range: -3.6068

Max Act: 2.9576. Min Act: -0.0000

Data Index: 264393 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 3.6068. Min Range: -3.6068

Max Act: 3.0990. Min Act: -0.0001

Data Index: 932134 (C4 (Web Text))

Max Activating Token Index: 400