Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3798. Min Act: -0.0002

Data Index: 691310 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.4003. Min Act: -0.0002

Data Index: 919998 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.4095. Min Act: -0.0002

Data Index: 934379 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3191. Min Act: -0.0002

Data Index: 1128500 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3320. Min Act: -0.0002

Data Index: 612222 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3226. Min Act: -0.0001

Data Index: 1316324 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3460. Min Act: -0.0002

Data Index: 543802 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3702. Min Act: -0.0001

Data Index: 317003 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3383. Min Act: -0.0002

Data Index: 852172 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3019. Min Act: -0.0001

Data Index: 790521 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.2074. Min Act: -0.0002

Data Index: 1346729 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.2452. Min Act: -0.0001

Data Index: 787384 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1496. Min Act: -0.0001

Data Index: 115535 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1799. Min Act: -0.0001

Data Index: 891881 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1771. Min Act: -0.0001

Data Index: 171326 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1493. Min Act: -0.0002

Data Index: 305046 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1704. Min Act: -0.0002

Data Index: 911423 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1699. Min Act: -0.0002

Data Index: 1310059 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1476. Min Act: -0.0001

Data Index: 1107291 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1790. Min Act: -0.0002

Data Index: 1120509 (C4 (Web Text))

Max Activating Token Index: 996