Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1216. Min Act: -0.0001

Data Index: 838979 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1220. Min Act: -0.0001

Data Index: 237133 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1327. Min Act: -0.0001

Data Index: 195395 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1285. Min Act: -0.0001

Data Index: 452126 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1022944 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1238. Min Act: -0.0001

Data Index: 780051 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1190. Min Act: -0.0001

Data Index: 869800 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1001666 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1147. Min Act: -0.0001

Data Index: 223889 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1127. Min Act: -0.0001

Data Index: 638801 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1161. Min Act: -0.0001

Data Index: 847396 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1117. Min Act: -0.0001

Data Index: 474830 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1136. Min Act: -0.0001

Data Index: 295756 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1121. Min Act: -0.0001

Data Index: 401024 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1152. Min Act: -0.0001

Data Index: 789787 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1306666 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1105. Min Act: -0.0001

Data Index: 442824 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1075. Min Act: -0.0001

Data Index: 183453 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1185974 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1094. Min Act: -0.0001

Data Index: 574209 (C4 (Web Text))

Max Activating Token Index: 267