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

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

Neuron 3189 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9409. Min Act: -0.0001

Data Index: 973331 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9149. Min Act: -0.0001

Data Index: 430171 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9213. Min Act: -0.0001

Data Index: 342609 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8581. Min Act: -0.0001

Data Index: 486672 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8059. Min Act: -0.0001

Data Index: 1068266 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8289. Min Act: -0.0001

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7823. Min Act: -0.0001

Data Index: 330314 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8043. Min Act: -0.0001

Data Index: 997603 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7779. Min Act: -0.0001

Data Index: 1026843 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7963. Min Act: -0.0001

Data Index: 1288731 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1243308 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7637. Min Act: -0.0001

Data Index: 1112507 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7381. Min Act: -0.0001

Data Index: 308509 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1208493 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7865. Min Act: -0.0001

Data Index: 587765 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7747. Min Act: -0.0001

Data Index: 652545 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7389. Min Act: -0.0001

Data Index: 849660 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7565. Min Act: -0.0001

Data Index: 678753 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1015911 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8146. Min Act: -0.0001

Data Index: 725049 (C4 (Web Text))

Max Activating Token Index: 938