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

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

Neuron 2971 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.9541. Min Act: -0.0002

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.9171. Min Act: -0.0002

Data Index: 437755 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8891. Min Act: -0.0002

Data Index: 786701 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.9082. Min Act: -0.0003

Data Index: 209343 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.9063. Min Act: -0.0002

Data Index: 159512 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8853. Min Act: -0.0002

Data Index: 392281 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8656. Min Act: -0.0002

Data Index: 218643 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8795. Min Act: -0.0002

Data Index: 701191 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8693. Min Act: -0.0002

Data Index: 434663 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8637. Min Act: -0.0002

Data Index: 536292 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8622. Min Act: -0.0002

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8762. Min Act: -0.0002

Data Index: 513265 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8581. Min Act: -0.0002

Data Index: 592847 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8492. Min Act: -0.0002

Data Index: 849309 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8459. Min Act: -0.0002

Data Index: 630883 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8579. Min Act: -0.0002

Data Index: 235001 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8609. Min Act: -0.0002

Data Index: 853273 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8440. Min Act: -0.0002

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8401. Min Act: -0.0002

Data Index: 17474 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8531. Min Act: -0.0002

Data Index: 953372 (C4 (Web Text))

Max Activating Token Index: 56