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

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

Neuron 2105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8569. Min Range: -2.8569

Max Act: 2.8569. Min Act: -0.0000

Data Index: 979188 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 2.8569. Min Range: -2.8569

Max Act: 2.2180. Min Act: -0.0000

Data Index: 774252 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 2.8569. Min Range: -2.8569

Max Act: 2.5025. Min Act: -0.0000

Data Index: 257652 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.9374. Min Act: -0.0001

Data Index: 237104 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.7640. Min Act: -0.0000

Data Index: 1125907 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.8407. Min Act: -0.0000

Data Index: 1267176 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.7896. Min Act: -0.0000

Data Index: 196726 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.8676. Min Act: -0.0000

Data Index: 244207 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.8201. Min Act: -0.0000

Data Index: 309482 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.7734. Min Act: -0.0000

Data Index: 90506 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.8388. Min Act: -0.0000

Data Index: 371946 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6657. Min Act: -0.0000

Data Index: 571076 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6624. Min Act: -0.0001

Data Index: 51007 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.5850. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6219. Min Act: -0.0000

Data Index: 106941 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6969. Min Act: -0.0000

Data Index: 51559 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6213. Min Act: -0.0000

Data Index: 1207475 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.6811. Min Act: -0.0000

Data Index: 533599 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 2.8569. Min Range: -2.8569

Max Act: 1.5519. Min Act: -0.0000

Data Index: 53428 (C4 (Web Text))

Max Activating Token Index: 136