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

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

Neuron 608 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: 2.8574. Min Range: -2.8574

Max Act: 2.8574. Min Act: -0.0000

Data Index: 88906 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.7251. Min Act: -0.0000

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.4471. Min Act: -0.0000

Data Index: 469896 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.4998. Min Act: -0.0000

Data Index: 1124000 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.6407. Min Act: -0.0000

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.4297. Min Act: -0.0000

Data Index: 363248 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.2004. Min Act: -0.0000

Data Index: 894386 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.2682. Min Act: -0.0000

Data Index: 1163459 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.1285. Min Act: -0.0000

Data Index: 657730 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.2496. Min Act: -0.0000

Data Index: 197173 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.0620. Min Act: -0.0000

Data Index: 152640 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.1626. Min Act: -0.0000

Data Index: 453594 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.8574. Min Range: -2.8574

Max Act: 1.9706. Min Act: -0.0000

Data Index: 498105 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.0834. Min Act: -0.0000

Data Index: 297426 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.1641. Min Act: -0.0000

Data Index: 1086144 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.1673. Min Act: -0.0000

Data Index: 1263253 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 2.8574. Min Range: -2.8574

Max Act: 2.0016. Min Act: -0.0000

Data Index: 40052 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 2.8574. Min Range: -2.8574

Max Act: 1.9853. Min Act: -0.0000

Data Index: 971158 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.8574. Min Range: -2.8574

Max Act: 1.8842. Min Act: -0.0000

Data Index: 1340005 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.8574. Min Range: -2.8574

Max Act: 1.9574. Min Act: -0.0000

Data Index: 201967 (C4 (Web Text))

Max Activating Token Index: 120