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

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

Neuron 933 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0794. Min Range: -3.0794

Max Act: 3.0794. Min Act: -0.0000

Data Index: 230544 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.0794. Min Range: -3.0794

Max Act: 2.7255. Min Act: -0.0000

Data Index: 862824 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 3.0794. Min Range: -3.0794

Max Act: 2.7914. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 3.0794. Min Range: -3.0794

Max Act: 2.0102. Min Act: -0.0000

Data Index: 186189 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.9601. Min Act: -0.0000

Data Index: 1233763 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.3735. Min Act: -0.0000

Data Index: 1441645 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.4457. Min Act: -0.0000

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1308240 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1263227 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.3114. Min Act: -0.0000

Data Index: 686036 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.2557. Min Act: -0.0000

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.2792. Min Act: -0.0000

Data Index: 56697 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.1301. Min Act: -0.0000

Data Index: 707440 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.0613. Min Act: -0.0000

Data Index: 548718 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1289207 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1212740 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.0794. Min Range: -3.0794

Max Act: 1.0701. Min Act: -0.0000

Data Index: 318712 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 3.0794. Min Range: -3.0794

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1530476 (Python Code)

Max Activating Token Index: 637