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

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

Neuron 5694 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: 2.0537. Min Range: -2.0537

Max Act: 2.0537. Min Act: -0.0002

Data Index: 301493 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.8978. Min Act: -0.0003

Data Index: 1003012 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.9081. Min Act: -0.0002

Data Index: 544935 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.8156. Min Act: -0.0002

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.8472. Min Act: -0.0002

Data Index: 1187738 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.8882. Min Act: -0.0003

Data Index: 678283 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.8447. Min Act: -0.0002

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.7500. Min Act: -0.0002

Data Index: 652979 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.7481. Min Act: -0.0002

Data Index: 499861 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.7507. Min Act: -0.0002

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.7324. Min Act: -0.0003

Data Index: 820848 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6828. Min Act: -0.0002

Data Index: 724423 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6962. Min Act: -0.0003

Data Index: 767068 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6349. Min Act: -0.0002

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6642. Min Act: -0.0002

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6532. Min Act: -0.0003

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6451. Min Act: -0.0002

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6455. Min Act: -0.0002

Data Index: 365909 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6978. Min Act: -0.0002

Data Index: 246149 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.0537. Min Range: -2.0537

Max Act: 1.6783. Min Act: -0.0002

Data Index: 228090 (C4 (Web Text))

Max Activating Token Index: 786