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

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

Neuron 1015 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.4169. Min Act: -0.0000

Data Index: 793977 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.4381. Min Act: -0.0000

Data Index: 647 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1266490 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.2910. Min Act: -0.0000

Data Index: 968215 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.2530. Min Act: -0.0000

Data Index: 102391 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1175639 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1635. Min Act: -0.0000

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1349701 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1021709 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1341. Min Act: -0.0000

Data Index: 417251 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0914. Min Act: -0.0000

Data Index: 398186 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.1012. Min Act: -0.0000

Data Index: 898933 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0621. Min Act: -0.0000

Data Index: 149315 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0710. Min Act: -0.0000

Data Index: 551641 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0414. Min Act: -0.0000

Data Index: 424109 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0641. Min Act: -0.0000

Data Index: 537825 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1033315 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0524. Min Act: -0.0000

Data Index: 136034 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1249045 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.4381. Min Range: -1.4381

Max Act: 1.0863. Min Act: -0.0000

Data Index: 51492 (C4 (Web Text))

Max Activating Token Index: 226