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

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

Neuron 2297 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: 2.2574. Min Range: -2.2574

Max Act: 2.2574. Min Act: -0.0002

Data Index: 211389 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.2574. Min Range: -2.2574

Max Act: 2.1938. Min Act: -0.0002

Data Index: 353370 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.2574. Min Range: -2.2574

Max Act: 2.1857. Min Act: -0.0002

Data Index: 793682 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 2.2574. Min Range: -2.2574

Max Act: 2.1086. Min Act: -0.0002

Data Index: 354045 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9967. Min Act: -0.0002

Data Index: 273617 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 2.2574. Min Range: -2.2574

Max Act: 2.0358. Min Act: -0.0002

Data Index: 530021 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9829. Min Act: -0.0002

Data Index: 996135 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9518. Min Act: -0.0002

Data Index: 643792 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9539. Min Act: -0.0002

Data Index: 125070 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9358. Min Act: -0.0002

Data Index: 785306 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.8797. Min Act: -0.0002

Data Index: 623726 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9493. Min Act: -0.0002

Data Index: 875738 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9306. Min Act: -0.0002

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9577. Min Act: -0.0002

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.8747. Min Act: -0.0002

Data Index: 1266691 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9008. Min Act: -0.0002

Data Index: 249472 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9048. Min Act: -0.0002

Data Index: 778843 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9041. Min Act: -0.0002

Data Index: 1024135 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9260. Min Act: -0.0002

Data Index: 1251739 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.2574. Min Range: -2.2574

Max Act: 1.9335. Min Act: -0.0002

Data Index: 288266 (C4 (Web Text))

Max Activating Token Index: 626