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

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

Neuron 1593 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3375. Min Range: -3.3375

Max Act: 3.3375. Min Act: -0.0000

Data Index: 801595 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.3375. Min Range: -3.3375

Max Act: 3.0364. Min Act: -0.0000

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 3.3375. Min Range: -3.3375

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1080241 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.5219. Min Act: -0.0000

Data Index: 190721 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.6393. Min Act: -0.0000

Data Index: 108490 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.6367. Min Act: -0.0000

Data Index: 1086055 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.7259. Min Act: -0.0000

Data Index: 460652 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.5682. Min Act: -0.0000

Data Index: 343439 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.4243. Min Act: -0.0000

Data Index: 737895 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.3822. Min Act: -0.0000

Data Index: 770125 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.4426. Min Act: -0.0000

Data Index: 1271006 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.6931. Min Act: -0.0000

Data Index: 560170 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.4291. Min Act: -0.0000

Data Index: 629072 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.4346. Min Act: -0.0000

Data Index: 880724 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.4065. Min Act: -0.0000

Data Index: 279703 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.3799. Min Act: -0.0000

Data Index: 659007 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.3937. Min Act: -0.0000

Data Index: 652510 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.2168. Min Act: -0.0000

Data Index: 89060 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.3342. Min Act: -0.0000

Data Index: 121786 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.3375. Min Range: -3.3375

Max Act: 2.7115. Min Act: -0.0000

Data Index: 1290130 (C4 (Web Text))

Max Activating Token Index: 392