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

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

Neuron 3329 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: 1.7559. Min Range: -1.7559

Max Act: 1.7559. Min Act: -0.0002

Data Index: 472092 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.5534. Min Act: -0.0002

Data Index: 357972 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.5536. Min Act: -0.0002

Data Index: 303092 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4858. Min Act: -0.0002

Data Index: 1092611 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4243. Min Act: -0.0002

Data Index: 1338479 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3988. Min Act: -0.0003

Data Index: 6447 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1665. Min Act: -0.0002

Data Index: 1315013 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1763. Min Act: -0.0002

Data Index: 518241 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1758. Min Act: -0.0003

Data Index: 1037052 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1079. Min Act: -0.0002

Data Index: 1197328 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1247. Min Act: -0.0002

Data Index: 75872 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.0857. Min Act: -0.0002

Data Index: 446448 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1132. Min Act: -0.0002

Data Index: 1264004 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1025. Min Act: -0.0002

Data Index: 1163935 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.0309. Min Act: -0.0002

Data Index: 895644 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9995. Min Act: -0.0002

Data Index: 715350 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9968. Min Act: -0.0002

Data Index: 1061636 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9939. Min Act: -0.0003

Data Index: 1279554 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9649. Min Act: -0.0002

Data Index: 1261534 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9824. Min Act: -0.0002

Data Index: 741542 (C4 (Web Text))

Max Activating Token Index: 126