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

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

Neuron 1495 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: 0.4183. Min Range: -0.4183

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1379373 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1388142 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1389731 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1033489 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1495712 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3424. Min Act: -0.0000

Data Index: 942684 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1574927 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1590781 (Python Code)

Max Activating Token Index: 817

Text #8

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1498388 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1425791 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1591670 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1131017 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1458453 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3315. Min Act: -0.0000

Data Index: 444676 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1523760 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1513483 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1508313 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1481504 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 0.4183. Min Range: -0.4183

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1604019 (Python Code)

Max Activating Token Index: 269