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

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

Neuron 4544 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2808. Min Act: -0.0000

Data Index: 776423 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2607. Min Act: -0.0000

Data Index: 530023 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1272656 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2221. Min Act: -0.0000

Data Index: 484639 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1158857 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1159224 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2084. Min Act: -0.0000

Data Index: 518159 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2061. Min Act: -0.0000

Data Index: 236184 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1116890 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2072. Min Act: -0.0000

Data Index: 161116 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1902. Min Act: -0.0000

Data Index: 794865 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1924. Min Act: -0.0000

Data Index: 965657 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1969. Min Act: -0.0000

Data Index: 741209 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1863. Min Act: -0.0000

Data Index: 823571 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1909. Min Act: -0.0000

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1881. Min Act: -0.0000

Data Index: 960840 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1244412 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1215109 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1665. Min Act: -0.0000

Data Index: 188084 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1773. Min Act: -0.0000

Data Index: 9282 (C4 (Web Text))

Max Activating Token Index: 444