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

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

Neuron 1695 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0003

Data Index: 715952 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1233. Min Act: -0.0003

Data Index: 551816 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1087432 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1166. Min Act: -0.0003

Data Index: 585888 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1165. Min Act: -0.0003

Data Index: 311949 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1154. Min Act: -0.0003

Data Index: 103609 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1122. Min Act: -0.0003

Data Index: 684516 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1156. Min Act: -0.0003

Data Index: 111370 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1106. Min Act: -0.0004

Data Index: 396152 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1069. Min Act: -0.0004

Data Index: 445491 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1317900 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1100. Min Act: -0.0003

Data Index: 514726 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1104. Min Act: -0.0003

Data Index: 641933 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1020. Min Act: -0.0003

Data Index: 142621 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1049. Min Act: -0.0003

Data Index: 1279055 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1051. Min Act: -0.0003

Data Index: 722339 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1049. Min Act: -0.0003

Data Index: 665552 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1093159 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1024. Min Act: -0.0003

Data Index: 774728 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0983. Min Act: -0.0004

Data Index: 945516 (C4 (Web Text))

Max Activating Token Index: 416