Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1692 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0003

Data Index: 1161207 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5244. Min Act: -0.0003

Data Index: 481804 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5144. Min Act: -0.0003

Data Index: 602792 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4708. Min Act: -0.0003

Data Index: 510536 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4729. Min Act: -0.0003

Data Index: 1298814 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5017. Min Act: -0.0004

Data Index: 608560 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4509. Min Act: -0.0003

Data Index: 31611 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4351. Min Act: -0.0003

Data Index: 174082 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4424. Min Act: -0.0003

Data Index: 1351659 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4305. Min Act: -0.0003

Data Index: 595271 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4158. Min Act: -0.0003

Data Index: 1185132 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4137. Min Act: -0.0003

Data Index: 305048 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4249. Min Act: -0.0003

Data Index: 1159024 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4081. Min Act: -0.0003

Data Index: 599734 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4089. Min Act: -0.0003

Data Index: 835732 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3942. Min Act: -0.0003

Data Index: 311018 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3874. Min Act: -0.0003

Data Index: 639098 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3853. Min Act: -0.0002

Data Index: 696192 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3828. Min Act: -0.0003

Data Index: 353928 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3957. Min Act: -0.0003

Data Index: 1239638 (C4 (Web Text))

Max Activating Token Index: 250