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

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

Neuron 2305 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2614. Min Range: -2.2614

Max Act: 2.2614. Min Act: -0.0000

Data Index: 126307 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.7222. Min Act: -0.0001

Data Index: 501233 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6795. Min Act: -0.0001

Data Index: 522148 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6751. Min Act: -0.0000

Data Index: 1165904 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.7708. Min Act: -0.0000

Data Index: 647750 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6474. Min Act: -0.0001

Data Index: 1304626 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5632. Min Act: -0.0000

Data Index: 731146 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1009509 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6540. Min Act: -0.0001

Data Index: 121050 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5495. Min Act: -0.0000

Data Index: 988030 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6258. Min Act: -0.0000

Data Index: 802739 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5244. Min Act: -0.0001

Data Index: 1335671 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5026. Min Act: -0.0000

Data Index: 148890 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5060. Min Act: -0.0000

Data Index: 743399 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.6651. Min Act: -0.0000

Data Index: 78913 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.3128. Min Act: -0.0001

Data Index: 779118 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.4628. Min Act: -0.0001

Data Index: 971981 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.3821. Min Act: -0.0001

Data Index: 1060530 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.5128. Min Act: -0.0001

Data Index: 233510 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 2.2614. Min Range: -2.2614

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1109810 (C4 (Web Text))

Max Activating Token Index: 607