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

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

Neuron 5252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1165. Min Range: -8.1165

Max Act: 8.1165. Min Act: -0.0000

Data Index: 1206719 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 8.1165. Min Range: -8.1165

Max Act: 7.6242. Min Act: -0.0000

Data Index: 296795 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 8.1165. Min Range: -8.1165

Max Act: 7.5558. Min Act: -0.0000

Data Index: 1332023 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 8.1165. Min Range: -8.1165

Max Act: 7.1650. Min Act: -0.0000

Data Index: 623932 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 8.1165. Min Range: -8.1165

Max Act: 7.2203. Min Act: -0.0000

Data Index: 661235 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.9061. Min Act: -0.0000

Data Index: 361776 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.3746. Min Act: -0.0000

Data Index: 1258529 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 8.1165. Min Range: -8.1165

Max Act: 7.2694. Min Act: -0.0000

Data Index: 1094257 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.7303. Min Act: -0.0000

Data Index: 159688 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.2969. Min Act: -0.0000

Data Index: 1178384 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.8061. Min Act: -0.0000

Data Index: 1118521 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.5689. Min Act: -0.0000

Data Index: 311545 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.3740. Min Act: -0.0000

Data Index: 403307 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.7308. Min Act: -0.0000

Data Index: 1233369 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.4660. Min Act: -0.0000

Data Index: 430141 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.2493. Min Act: -0.0000

Data Index: 1092669 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.2265. Min Act: -0.0000

Data Index: 1311434 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.1227. Min Act: -0.0000

Data Index: 24121 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.0367. Min Act: -0.0000

Data Index: 1281614 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 8.1165. Min Range: -8.1165

Max Act: 6.1673. Min Act: -0.0000

Data Index: 1127265 (C4 (Web Text))

Max Activating Token Index: 227