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

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

Neuron 4641 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: 1.5268. Min Range: -1.5268

Max Act: 1.5268. Min Act: -0.0000

Data Index: 139026 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.5268. Min Range: -1.5268

Max Act: 1.1756. Min Act: -0.0000

Data Index: 893257 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.5268. Min Range: -1.5268

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1180344 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.9957. Min Act: -0.0000

Data Index: 194349 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.8535. Min Act: -0.0000

Data Index: 287440 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.9211. Min Act: -0.0000

Data Index: 985895 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.9486. Min Act: -0.0000

Data Index: 265666 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1282220 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.9165. Min Act: -0.0000

Data Index: 781819 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.9173. Min Act: -0.0000

Data Index: 335937 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.8822. Min Act: -0.0000

Data Index: 213849 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.8213. Min Act: -0.0000

Data Index: 724614 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7574. Min Act: -0.0000

Data Index: 522007 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7421. Min Act: -0.0000

Data Index: 7951 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7052. Min Act: -0.0000

Data Index: 501024 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7825. Min Act: -0.0000

Data Index: 878787 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.6836. Min Act: -0.0000

Data Index: 431206 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.6711. Min Act: -0.0000

Data Index: 844131 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7106. Min Act: -0.0000

Data Index: 53157 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.5268. Min Range: -1.5268

Max Act: 0.7140. Min Act: -0.0000

Data Index: 276234 (C4 (Web Text))

Max Activating Token Index: 242