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

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

Neuron 2642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3593. Min Act: -0.0001

Data Index: 867484 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3738. Min Act: -0.0001

Data Index: 152914 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3237. Min Act: -0.0000

Data Index: 833802 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2596. Min Act: -0.0000

Data Index: 416503 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2228. Min Act: -0.0000

Data Index: 532023 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2134. Min Act: -0.0001

Data Index: 276324 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2209. Min Act: -0.0000

Data Index: 13590 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1967. Min Act: -0.0000

Data Index: 730232 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1216113 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1981. Min Act: -0.0001

Data Index: 411002 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1901. Min Act: -0.0000

Data Index: 72017 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1741. Min Act: -0.0001

Data Index: 917309 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1092909 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1830. Min Act: -0.0001

Data Index: 872352 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1016253 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1835. Min Act: -0.0000

Data Index: 772967 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1169842 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2153. Min Act: -0.0000

Data Index: 695446 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1774. Min Act: -0.0001

Data Index: 5150 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.1769. Min Act: -0.0001

Data Index: 815293 (C4 (Web Text))

Max Activating Token Index: 138