Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 575 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.9338. Min Act: -0.0001

Data Index: 764250 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.7386. Min Act: -0.0001

Data Index: 1079496 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.7062. Min Act: -0.0001

Data Index: 1248567 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.5170. Min Act: -0.0001

Data Index: 1095653 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.3452. Min Act: -0.0001

Data Index: 319204 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.4844. Min Act: -0.0001

Data Index: 306576 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.3952. Min Act: -0.0001

Data Index: 517382 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.3444. Min Act: -0.0001

Data Index: 65181 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.3276. Min Act: -0.0001

Data Index: 85318 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.3008. Min Act: -0.0001

Data Index: 205217 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1370. Min Act: -0.0001

Data Index: 1068761 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1154. Min Act: -0.0001

Data Index: 165406 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.2788. Min Act: -0.0001

Data Index: 1082043 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.2164. Min Act: -0.0001

Data Index: 179698 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1774. Min Act: -0.0001

Data Index: 321368 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1380. Min Act: -0.0001

Data Index: 226111 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1039. Min Act: -0.0001

Data Index: 59677 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1482. Min Act: -0.0001

Data Index: 171854 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1794. Min Act: -0.0001

Data Index: 28298 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 1.9338. Min Range: -1.9338

Max Act: 1.1669. Min Act: -0.0001

Data Index: 1254865 (C4 (Web Text))

Max Activating Token Index: 712