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

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

Neuron 5288 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8701. Min Range: -2.8701

Max Act: 2.8701. Min Act: -0.0000

Data Index: 104949 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 2.8701. Min Range: -2.8701

Max Act: 2.6933. Min Act: -0.0000

Data Index: 338758 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 2.8701. Min Range: -2.8701

Max Act: 2.2763. Min Act: -0.0000

Data Index: 1084468 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 2.8701. Min Range: -2.8701

Max Act: 2.2699. Min Act: -0.0000

Data Index: 96391 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.8340. Min Act: -0.0000

Data Index: 138922 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.9322. Min Act: -0.0000

Data Index: 543554 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.8264. Min Act: -0.0000

Data Index: 676622 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1185147 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.8588. Min Act: -0.0000

Data Index: 976143 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1119841 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.7114. Min Act: -0.0000

Data Index: 511712 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.7043. Min Act: -0.0000

Data Index: 252861 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.7059. Min Act: -0.0000

Data Index: 716404 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1211514 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6682. Min Act: -0.0000

Data Index: 429214 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6608. Min Act: -0.0000

Data Index: 94603 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1103068 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1307672 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1151445 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 2.8701. Min Range: -2.8701

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1253405 (C4 (Web Text))

Max Activating Token Index: 893