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

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

Neuron 2630 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: 2.4736. Min Range: -2.4736

Max Act: 2.4736. Min Act: -0.0000

Data Index: 1591424 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 2.4736. Min Range: -2.4736

Max Act: 2.2818. Min Act: -0.0000

Data Index: 1414953 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 2.4736. Min Range: -2.4736

Max Act: 2.1045. Min Act: -0.0000

Data Index: 1610765 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.9872. Min Act: -0.0000

Data Index: 1477408 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1447146 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 2.4736. Min Range: -2.4736

Max Act: 2.0215. Min Act: -0.0000

Data Index: 1552744 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8021. Min Act: -0.0000

Data Index: 1467199 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1398758 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8678. Min Act: -0.0000

Data Index: 1526417 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.9643. Min Act: -0.0000

Data Index: 1644880 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1445491 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.7571. Min Act: -0.0000

Data Index: 1427348 (Python Code)

Max Activating Token Index: 391

Text #12

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.7467. Min Act: -0.0000

Data Index: 1397211 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.9040. Min Act: -0.0000

Data Index: 1463798 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1625882 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8317. Min Act: -0.0000

Data Index: 1412017 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1414969 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.7728. Min Act: 0.0000

Data Index: 1581798 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1390788 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 2.4736. Min Range: -2.4736

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1643809 (Python Code)

Max Activating Token Index: 665