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

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

Neuron 4188 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5457. Min Act: -0.0001

Data Index: 824995 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4918. Min Act: -0.0001

Data Index: 861135 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4589. Min Act: -0.0001

Data Index: 355664 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5495. Min Act: -0.0001

Data Index: 381665 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5519. Min Act: -0.0001

Data Index: 867281 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5079. Min Act: -0.0001

Data Index: 1062429 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5150. Min Act: -0.0001

Data Index: 852282 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4677. Min Act: -0.0001

Data Index: 893275 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4564. Min Act: -0.0001

Data Index: 268363 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5106. Min Act: -0.0001

Data Index: 207095 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4558. Min Act: -0.0001

Data Index: 117984 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4740. Min Act: -0.0001

Data Index: 591386 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5467. Min Act: -0.0001

Data Index: 721442 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1128884 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4658. Min Act: -0.0001

Data Index: 322190 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.5087. Min Act: -0.0001

Data Index: 1214563 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4657. Min Act: -0.0001

Data Index: 489881 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4074. Min Act: -0.0002

Data Index: 913535 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4764. Min Act: -0.0001

Data Index: 31203 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4579. Min Act: -0.0001

Data Index: 612767 (C4 (Web Text))

Max Activating Token Index: 211