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

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

Neuron 3537 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: 1.4446. Min Range: -1.4446

Max Act: 1.4446. Min Act: -0.0000

Data Index: 612408 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1022454 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3891. Min Act: -0.0000

Data Index: 268423 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3734. Min Act: -0.0000

Data Index: 52876 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.2511. Min Act: -0.0000

Data Index: 435674 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3102. Min Act: -0.0000

Data Index: 1417541 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3603. Min Act: -0.0000

Data Index: 962034 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1995. Min Act: -0.0000

Data Index: 300093 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1012525 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1517. Min Act: -0.0000

Data Index: 283396 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.2166. Min Act: -0.0000

Data Index: 231779 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1999. Min Act: -0.0000

Data Index: 927333 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1524479 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1053682 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1587. Min Act: -0.0000

Data Index: 274422 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1311351 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1026991 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1150. Min Act: -0.0000

Data Index: 934390 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1325111 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 805