Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2285 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5840. Min Act: -0.0000

Data Index: 416997 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5524. Min Act: -0.0000

Data Index: 540576 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5385. Min Act: -0.0000

Data Index: 277292 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4804. Min Act: -0.0000

Data Index: 526666 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5066. Min Act: -0.0000

Data Index: 232764 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1345135 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4839. Min Act: -0.0000

Data Index: 852978 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1029612 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4547. Min Act: 0.0000

Data Index: 171813 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4104. Min Act: -0.0000

Data Index: 296145 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4284. Min Act: -0.0000

Data Index: 361094 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4343. Min Act: -0.0000

Data Index: 504385 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4474. Min Act: -0.0000

Data Index: 74352 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4354. Min Act: 0.0000

Data Index: 144346 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4078. Min Act: -0.0000

Data Index: 323361 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1007298 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4132. Min Act: -0.0000

Data Index: 158454 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4255. Min Act: -0.0000

Data Index: 712657 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4411. Min Act: 0.0000

Data Index: 42931 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4030. Min Act: -0.0000

Data Index: 833526 (C4 (Web Text))

Max Activating Token Index: 290