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

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

Neuron 390 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.2398. Min Act: -0.0001

Data Index: 1140003 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0897. Min Act: -0.0001

Data Index: 665559 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0793. Min Act: -0.0001

Data Index: 1039166 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.1157. Min Act: -0.0001

Data Index: 197789 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0947. Min Act: -0.0001

Data Index: 610865 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0902. Min Act: -0.0001

Data Index: 234972 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0419. Min Act: -0.0001

Data Index: 458458 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0869. Min Act: -0.0001

Data Index: 311157 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0856. Min Act: -0.0001

Data Index: 334301 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0739. Min Act: -0.0001

Data Index: 466260 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.2398. Min Range: -1.2398

Max Act: 0.9372. Min Act: -0.0001

Data Index: 524427 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0582. Min Act: -0.0001

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0125. Min Act: -0.0001

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0937. Min Act: -0.0001

Data Index: 49752 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1120403 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0220. Min Act: -0.0001

Data Index: 598485 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0094. Min Act: -0.0001

Data Index: 971112 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.1410. Min Act: -0.0001

Data Index: 329870 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.2398. Min Range: -1.2398

Max Act: 0.9427. Min Act: -0.0001

Data Index: 90948 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.2398. Min Range: -1.2398

Max Act: 1.0573. Min Act: -0.0001

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 140