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

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

Neuron 1596 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0001

Data Index: 893999 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1173833 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5635. Min Act: -0.0001

Data Index: 747868 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6360. Min Act: -0.0001

Data Index: 858635 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5904. Min Act: -0.0001

Data Index: 87571 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5873. Min Act: -0.0001

Data Index: 59670 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5777. Min Act: -0.0001

Data Index: 266402 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1175224 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5599. Min Act: -0.0001

Data Index: 1111882 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5906. Min Act: -0.0001

Data Index: 959590 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5896. Min Act: -0.0001

Data Index: 260248 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4848. Min Act: -0.0001

Data Index: 672937 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5757. Min Act: -0.0001

Data Index: 995363 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5315. Min Act: -0.0001

Data Index: 324758 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5288. Min Act: -0.0001

Data Index: 33248 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5416. Min Act: -0.0001

Data Index: 114064 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5229. Min Act: -0.0001

Data Index: 561487 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5379. Min Act: -0.0001

Data Index: 717413 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5549. Min Act: -0.0001

Data Index: 92531 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5418. Min Act: -0.0001

Data Index: 915645 (C4 (Web Text))

Max Activating Token Index: 520