Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2057 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2150. Min Act: -0.0001

Data Index: 580410 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1994. Min Act: -0.0000

Data Index: 306887 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2050. Min Act: -0.0001

Data Index: 708307 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2032. Min Act: -0.0001

Data Index: 75142 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2082. Min Act: -0.0001

Data Index: 278769 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2056. Min Act: -0.0001

Data Index: 88844 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1010378 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1957. Min Act: -0.0001

Data Index: 13590 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1924. Min Act: -0.0000

Data Index: 367312 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1984. Min Act: -0.0001

Data Index: 838035 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1849. Min Act: -0.0000

Data Index: 316853 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1247241 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1771. Min Act: -0.0000

Data Index: 195081 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1128140 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1121813 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1065928 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1764. Min Act: -0.0000

Data Index: 826183 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1785. Min Act: -0.0000

Data Index: 532226 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1359836 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1625037 (Python Code)

Max Activating Token Index: 812