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

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

Neuron 1118 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: 0.2637. Min Range: -0.2637

Max Act: 0.2540. Min Act: -0.0001

Data Index: 343718 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2637. Min Act: -0.0000

Data Index: 840512 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2049. Min Act: -0.0000

Data Index: 539421 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2277. Min Act: -0.0000

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1632568 (Python Code)

Max Activating Token Index: 884

Text #5

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2169. Min Act: -0.0000

Data Index: 39732 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1296250 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2198. Min Act: -0.0000

Data Index: 860750 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2038. Min Act: -0.0001

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2031. Min Act: -0.0001

Data Index: 796033 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2091. Min Act: -0.0000

Data Index: 702346 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1080480 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1434245 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1862. Min Act: -0.0001

Data Index: 571175 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1403727 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1798. Min Act: -0.0001

Data Index: 329240 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1500223 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1851. Min Act: -0.0000

Data Index: 762589 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1714. Min Act: -0.0000

Data Index: 724733 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1874. Min Act: -0.0001

Data Index: 366875 (C4 (Web Text))

Max Activating Token Index: 874