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

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

Neuron 3968 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: 1.4658. Min Range: -1.4658

Max Act: 1.4658. Min Act: -0.0000

Data Index: 632975 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2141. Min Act: -0.0001

Data Index: 14446 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2144. Min Act: -0.0001

Data Index: 347356 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1013. Min Act: -0.0001

Data Index: 831999 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1304412 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0419. Min Act: -0.0000

Data Index: 334964 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1380. Min Act: -0.0001

Data Index: 1069837 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0310. Min Act: -0.0001

Data Index: 192736 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0342. Min Act: -0.0000

Data Index: 455430 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0929. Min Act: -0.0001

Data Index: 544517 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0503. Min Act: -0.0001

Data Index: 721400 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0499. Min Act: -0.0000

Data Index: 606879 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1133. Min Act: -0.0001

Data Index: 126125 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0633. Min Act: -0.0001

Data Index: 271669 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0294. Min Act: -0.0000

Data Index: 387761 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0197. Min Act: -0.0001

Data Index: 761251 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9795. Min Act: -0.0001

Data Index: 273253 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0472. Min Act: -0.0001

Data Index: 1185844 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1058973 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0085. Min Act: -0.0001

Data Index: 714828 (C4 (Web Text))

Max Activating Token Index: 873