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

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

Neuron 1945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.8055. Min Act: -0.0003

Data Index: 1144245 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7407. Min Act: -0.0003

Data Index: 888575 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7339. Min Act: -0.0003

Data Index: 1066880 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7040. Min Act: -0.0003

Data Index: 501568 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7035. Min Act: -0.0003

Data Index: 1162872 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7270. Min Act: -0.0003

Data Index: 61776 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6776. Min Act: -0.0003

Data Index: 845271 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6511. Min Act: -0.0003

Data Index: 577122 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6690. Min Act: -0.0003

Data Index: 232407 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6659. Min Act: -0.0003

Data Index: 300449 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6545. Min Act: -0.0003

Data Index: 355739 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6531. Min Act: -0.0003

Data Index: 1276828 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6191. Min Act: -0.0003

Data Index: 630297 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6340. Min Act: -0.0003

Data Index: 57800 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6281. Min Act: -0.0003

Data Index: 1356191 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6461. Min Act: -0.0003

Data Index: 1287624 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6174. Min Act: -0.0003

Data Index: 365840 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6166. Min Act: -0.0003

Data Index: 616439 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6137. Min Act: -0.0003

Data Index: 612721 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6126. Min Act: -0.0003

Data Index: 1100231 (C4 (Web Text))

Max Activating Token Index: 301