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

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

Neuron 93 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9690. Min Act: -0.0000

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.0682. Min Range: -1.0682

Max Act: 1.0682. Min Act: -0.0000

Data Index: 220294 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9114. Min Act: -0.0000

Data Index: 917668 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9084. Min Act: -0.0000

Data Index: 696480 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7692. Min Act: -0.0000

Data Index: 231388 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8943. Min Act: -0.0000

Data Index: 264568 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8573. Min Act: -0.0000

Data Index: 169166 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8294. Min Act: -0.0000

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8211. Min Act: -0.0000

Data Index: 3220 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.9173. Min Act: -0.0000

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8139. Min Act: -0.0000

Data Index: 283813 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8109. Min Act: -0.0000

Data Index: 701203 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7796. Min Act: -0.0000

Data Index: 160430 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7907. Min Act: -0.0000

Data Index: 468004 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7933. Min Act: -0.0000

Data Index: 24844 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8060. Min Act: -0.0000

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.8843. Min Act: -0.0000

Data Index: 666821 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7560. Min Act: -0.0000

Data Index: 653371 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1311897 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.0682. Min Range: -1.0682

Max Act: 0.7682. Min Act: -0.0000

Data Index: 310279 (C4 (Web Text))

Max Activating Token Index: 702