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

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

Neuron 3445 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1351038 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.4246. Min Act: -0.0000

Data Index: 522048 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3639. Min Act: -0.0000

Data Index: 763399 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3009. Min Act: -0.0000

Data Index: 311986 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1588804 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1563372 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3234. Min Act: -0.0000

Data Index: 657634 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3561. Min Act: -0.0000

Data Index: 72391 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1536031 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2719. Min Act: -0.0000

Data Index: 824794 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.3012. Min Act: -0.0000

Data Index: 589291 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2711. Min Act: -0.0000

Data Index: 313244 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1129993 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2657. Min Act: -0.0000

Data Index: 93674 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1088102 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1548051 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1593569 (Python Code)

Max Activating Token Index: 919

Text #17

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2834. Min Act: -0.0000

Data Index: 536064 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1555958 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.5196. Min Range: -0.5196

Max Act: 0.2168. Min Act: -0.0000

Data Index: 693221 (C4 (Web Text))

Max Activating Token Index: 970