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

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

Neuron 272 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2626. Min Range: -2.2626

Max Act: 2.2626. Min Act: -0.0000

Data Index: 742575 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 2.2626. Min Range: -2.2626

Max Act: 2.0212. Min Act: -0.0000

Data Index: 762019 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.8994. Min Act: -0.0000

Data Index: 1049278 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.8677. Min Act: -0.0000

Data Index: 121418 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.8165. Min Act: -0.0000

Data Index: 230056 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7645. Min Act: -0.0000

Data Index: 433206 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7555. Min Act: -0.0000

Data Index: 185915 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1007960 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7094. Min Act: -0.0000

Data Index: 307725 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.5820. Min Act: -0.0000

Data Index: 600134 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.6704. Min Act: -0.0000

Data Index: 495995 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1271069 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.6512. Min Act: -0.0000

Data Index: 933337 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1322317 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.7128. Min Act: -0.0000

Data Index: 141143 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.6145. Min Act: -0.0000

Data Index: 103369 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.6045. Min Act: -0.0000

Data Index: 825597 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.5067. Min Act: -0.0000

Data Index: 337694 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1218063 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.5579. Min Act: -0.0000

Data Index: 446047 (C4 (Web Text))

Max Activating Token Index: 589