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

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

Neuron 2339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1574. Min Range: -4.1574

Max Act: 4.1574. Min Act: -0.0000

Data Index: 94227 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.9205. Min Act: -0.0000

Data Index: 825724 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.7710. Min Act: -0.0000

Data Index: 611306 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.8278. Min Act: -0.0000

Data Index: 749420 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.4372. Min Act: -0.0000

Data Index: 722919 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.5230. Min Act: -0.0000

Data Index: 1054605 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.6204. Min Act: -0.0000

Data Index: 746262 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.6259. Min Act: -0.0000

Data Index: 1243512 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.4277. Min Act: -0.0000

Data Index: 393847 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.5743. Min Act: -0.0000

Data Index: 421544 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.4669. Min Act: -0.0000

Data Index: 971052 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.2848. Min Act: -0.0000

Data Index: 1059914 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.4035. Min Act: -0.0000

Data Index: 676197 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.0509. Min Act: -0.0000

Data Index: 1339050 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.4277. Min Act: -0.0000

Data Index: 1359023 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.1153. Min Act: -0.0000

Data Index: 1128059 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.2393. Min Act: -0.0000

Data Index: 1270412 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.1013. Min Act: -0.0000

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.0768. Min Act: -0.0000

Data Index: 960907 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 4.1574. Min Range: -4.1574

Max Act: 3.2354. Min Act: -0.0000

Data Index: 1304220 (C4 (Web Text))

Max Activating Token Index: 143