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

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

Neuron 979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.6163. Min Act: -0.0002

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.4192. Min Act: -0.0002

Data Index: 1210600 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.3098. Min Act: -0.0002

Data Index: 1301381 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.2908. Min Act: -0.0002

Data Index: 203952 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.1462. Min Act: -0.0002

Data Index: 575 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0480. Min Act: -0.0002

Data Index: 1626093 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0566. Min Act: -0.0002

Data Index: 815555 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0626. Min Act: -0.0002

Data Index: 397281 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.1241. Min Act: -0.0002

Data Index: 1003947 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0295. Min Act: -0.0002

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0572. Min Act: -0.0002

Data Index: 1462846 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9735. Min Act: -0.0002

Data Index: 1464200 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0078. Min Act: -0.0002

Data Index: 936461 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0166. Min Act: -0.0002

Data Index: 1437707 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9934. Min Act: -0.0002

Data Index: 554636 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.6163. Min Range: -1.6163

Max Act: 1.0519. Min Act: -0.0002

Data Index: 800626 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9875. Min Act: -0.0002

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9762. Min Act: -0.0002

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9870. Min Act: -0.0002

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.6163. Min Range: -1.6163

Max Act: 0.9874. Min Act: -0.0002

Data Index: 677297 (C4 (Web Text))

Max Activating Token Index: 501