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

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

Neuron 2701 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.3027. Min Act: -0.0001

Data Index: 885901 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1174398 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2576. Min Act: -0.0001

Data Index: 782703 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2725. Min Act: -0.0001

Data Index: 907001 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2326. Min Act: -0.0000

Data Index: 998503 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1149914 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1046750 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2417. Min Act: -0.0000

Data Index: 591420 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2471. Min Act: -0.0001

Data Index: 382829 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2309. Min Act: -0.0000

Data Index: 526572 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2330. Min Act: -0.0000

Data Index: 221919 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2294. Min Act: -0.0000

Data Index: 601437 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2257. Min Act: -0.0000

Data Index: 800737 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2254. Min Act: -0.0000

Data Index: 118832 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2115. Min Act: -0.0000

Data Index: 188425 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2243. Min Act: -0.0000

Data Index: 576783 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2227. Min Act: -0.0001

Data Index: 1056811 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2112. Min Act: -0.0000

Data Index: 604118 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2124. Min Act: -0.0001

Data Index: 464407 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.3027. Min Range: -0.3027

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1090715 (C4 (Web Text))

Max Activating Token Index: 998