Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4481 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6671. Min Act: -0.0000

Data Index: 647461 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6985. Min Act: -0.0000

Data Index: 767880 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6581. Min Act: -0.0000

Data Index: 865765 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6165. Min Act: -0.0000

Data Index: 138525 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4759. Min Act: -0.0000

Data Index: 258847 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1110547 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1023567 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5571. Min Act: -0.0000

Data Index: 154302 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1343517 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1001147 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4423. Min Act: -0.0000

Data Index: 605836 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1125611 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1292263 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3605. Min Act: -0.0000

Data Index: 12110 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3379. Min Act: -0.0000

Data Index: 45307 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1218142 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3410. Min Act: -0.0000

Data Index: 426486 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1128788 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3121. Min Act: -0.0000

Data Index: 85747 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.3135. Min Act: -0.0000

Data Index: 287430 (C4 (Web Text))

Max Activating Token Index: 429