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

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

Neuron 3701 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: 0.3397. Min Range: -0.3397

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1526115 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3347. Min Act: -0.0002

Data Index: 112155 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3206. Min Act: -0.0001

Data Index: 603401 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2776. Min Act: -0.0001

Data Index: 707210 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1571981 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3025. Min Act: -0.0002

Data Index: 239463 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1307047 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2794. Min Act: -0.0002

Data Index: 1139440 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1161677 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2863. Min Act: -0.0001

Data Index: 641059 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1369253 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2785. Min Act: -0.0002

Data Index: 1050661 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1564840 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2811. Min Act: -0.0002

Data Index: 497639 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2877. Min Act: -0.0002

Data Index: 560430 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2836. Min Act: -0.0002

Data Index: 282605 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2757. Min Act: -0.0002

Data Index: 811887 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2727. Min Act: -0.0001

Data Index: 1027013 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2642. Min Act: -0.0002

Data Index: 984788 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1649416 (Python Code)

Max Activating Token Index: 385