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

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

Neuron 3198 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: 0.9374. Min Range: -0.9374

Max Act: 0.9374. Min Act: -0.0001

Data Index: 1310996 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.8063. Min Act: -0.0001

Data Index: 251371 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.8118. Min Act: -0.0001

Data Index: 1262941 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7654. Min Act: -0.0001

Data Index: 939024 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7278. Min Act: -0.0001

Data Index: 1212613 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7056. Min Act: -0.0001

Data Index: 842328 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5880. Min Act: -0.0001

Data Index: 248113 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1027667 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6503. Min Act: -0.0001

Data Index: 140309 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6782. Min Act: -0.0001

Data Index: 863245 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6574. Min Act: -0.0001

Data Index: 274127 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6552. Min Act: -0.0001

Data Index: 1319843 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6371. Min Act: -0.0001

Data Index: 676107 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6384. Min Act: -0.0001

Data Index: 897982 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6347. Min Act: -0.0001

Data Index: 446270 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6116. Min Act: -0.0001

Data Index: 473842 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6116. Min Act: -0.0001

Data Index: 318631 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5886. Min Act: -0.0001

Data Index: 1120299 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1160471 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7132. Min Act: -0.0001

Data Index: 679117 (C4 (Web Text))

Max Activating Token Index: 744