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

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

Neuron 3648 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1405. Min Range: -2.1405

Max Act: 2.1405. Min Act: -0.0002

Data Index: 122807 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 2.1405. Min Range: -2.1405

Max Act: 2.0320. Min Act: -0.0002

Data Index: 347351 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.9707. Min Act: -0.0002

Data Index: 1220004 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.8468. Min Act: -0.0002

Data Index: 554255 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.9150. Min Act: -0.0002

Data Index: 893743 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.9257. Min Act: -0.0002

Data Index: 406960 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7727. Min Act: -0.0002

Data Index: 1126323 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.8391. Min Act: -0.0002

Data Index: 1278314 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7459. Min Act: -0.0002

Data Index: 1086472 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7306. Min Act: -0.0002

Data Index: 1226140 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.8128. Min Act: -0.0002

Data Index: 135936 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7776. Min Act: -0.0002

Data Index: 309269 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7649. Min Act: -0.0002

Data Index: 716407 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7966. Min Act: -0.0002

Data Index: 717967 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7695. Min Act: -0.0002

Data Index: 385745 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7776. Min Act: -0.0002

Data Index: 40797 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7879. Min Act: -0.0002

Data Index: 11399 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7084. Min Act: -0.0002

Data Index: 602771 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7209. Min Act: -0.0002

Data Index: 1042602 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.1405. Min Range: -2.1405

Max Act: 1.7465. Min Act: -0.0002

Data Index: 394948 (C4 (Web Text))

Max Activating Token Index: 486