Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.6018. Min Act: -0.0001

Data Index: 1155190 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.6369. Min Act: -0.0001

Data Index: 313320 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5789. Min Act: -0.0001

Data Index: 356448 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5422. Min Act: -0.0001

Data Index: 1090331 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5569. Min Act: -0.0001

Data Index: 540920 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5291. Min Act: -0.0001

Data Index: 978407 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5292. Min Act: -0.0001

Data Index: 427783 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1072407 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5129. Min Act: -0.0001

Data Index: 906766 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4688. Min Act: -0.0001

Data Index: 581063 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4772. Min Act: -0.0001

Data Index: 387267 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4591. Min Act: -0.0001

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4472. Min Act: -0.0001

Data Index: 150094 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.5031. Min Act: -0.0001

Data Index: 139845 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4949. Min Act: -0.0001

Data Index: 35908 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4833. Min Act: -0.0001

Data Index: 207026 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4860. Min Act: -0.0001

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4616. Min Act: -0.0001

Data Index: 87033 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1147885 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.6369. Min Range: -0.6369

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1328833 (C4 (Web Text))

Max Activating Token Index: 443