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

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

Neuron 3821 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.5131. Min Act: -0.0000

Data Index: 129357 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.4280. Min Act: -0.0000

Data Index: 803370 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.3119. Min Act: -0.0000

Data Index: 54351 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.2598. Min Act: -0.0000

Data Index: 360099 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.2512. Min Act: -0.0000

Data Index: 193999 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.2367. Min Act: -0.0000

Data Index: 671024 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.2220. Min Act: -0.0000

Data Index: 290911 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1930. Min Act: -0.0000

Data Index: 852464 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1933. Min Act: -0.0000

Data Index: 353818 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1323878 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1366. Min Act: -0.0000

Data Index: 948013 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1188. Min Act: 0.0000

Data Index: 628569 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1080. Min Act: -0.0000

Data Index: 102758 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1035. Min Act: -0.0000

Data Index: 181566 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1052. Min Act: -0.0000

Data Index: 977095 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.1009. Min Act: -0.0000

Data Index: 542180 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1350023 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.0864. Min Act: -0.0000

Data Index: 214298 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.0835. Min Act: -0.0000

Data Index: 455872 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 1.5131. Min Range: -1.5131

Max Act: 1.0735. Min Act: -0.0000

Data Index: 524984 (C4 (Web Text))

Max Activating Token Index: 413