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

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

Neuron 3935 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.4234. Min Act: -0.0000

Data Index: 741768 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.1013. Min Act: -0.0001

Data Index: 776843 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.0710. Min Act: -0.0000

Data Index: 445003 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.4234. Min Range: -1.4234

Max Act: 1.0391. Min Act: -0.0000

Data Index: 739514 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1301559 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9921. Min Act: -0.0001

Data Index: 911898 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9972. Min Act: -0.0000

Data Index: 810230 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9461. Min Act: -0.0000

Data Index: 184258 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9413. Min Act: -0.0000

Data Index: 730715 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9962. Min Act: -0.0000

Data Index: 741121 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1146499 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9501. Min Act: -0.0000

Data Index: 148754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9682. Min Act: -0.0001

Data Index: 59260 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9374. Min Act: -0.0000

Data Index: 775032 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9226. Min Act: -0.0001

Data Index: 14763 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1216215 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9215. Min Act: -0.0000

Data Index: 948538 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9356. Min Act: -0.0000

Data Index: 403679 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1582423 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 1.4234. Min Range: -1.4234

Max Act: 0.9522. Min Act: -0.0000

Data Index: 197055 (C4 (Web Text))

Max Activating Token Index: 867