Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2342 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1467597 (Python Code)

Max Activating Token Index: 506

Text #1

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7590. Min Act: -0.0000

Data Index: 412206 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1428088 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1645028 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1586165 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6818. Min Act: -0.0000

Data Index: 866799 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1586845 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1078790 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1649190 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1593919 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1522077 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1603828 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5844. Min Act: -0.0000

Data Index: 992671 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1455880 (Python Code)

Max Activating Token Index: 912

Text #14

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1502752 (Python Code)

Max Activating Token Index: 990

Text #15

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1376352 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1562212 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5415. Min Act: -0.0000

Data Index: 649133 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1548165 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1487712 (Python Code)

Max Activating Token Index: 524