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

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

Neuron 5012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2619. Min Act: -0.0000

Data Index: 995488 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2563. Min Act: -0.0001

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.2154. Min Act: -0.0000

Data Index: 801086 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1422. Min Act: -0.0000

Data Index: 922658 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1149274 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0745. Min Act: -0.0001

Data Index: 474206 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1648. Min Act: -0.0000

Data Index: 46175 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0551. Min Act: -0.0001

Data Index: 958996 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1663. Min Act: -0.0001

Data Index: 982270 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0570. Min Act: -0.0000

Data Index: 46022 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0514. Min Act: -0.0000

Data Index: 106603 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0111. Min Act: -0.0001

Data Index: 1287257 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0374. Min Act: -0.0001

Data Index: 1603354 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0676. Min Act: -0.0001

Data Index: 556352 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.1919. Min Act: -0.0001

Data Index: 713481 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0633. Min Act: -0.0000

Data Index: 806430 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1325284 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0681. Min Act: -0.0001

Data Index: 720811 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0360. Min Act: -0.0001

Data Index: 867020 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 1.2619. Min Range: -1.2619

Max Act: 1.0123. Min Act: -0.0001

Data Index: 800357 (C4 (Web Text))

Max Activating Token Index: 769