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

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

Neuron 4934 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: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1270895 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1145118 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0745. Min Act: -0.0002

Data Index: 519152 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0714. Min Act: -0.0002

Data Index: 142959 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0686. Min Act: -0.0002

Data Index: 115822 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0628. Min Act: -0.0002

Data Index: 929528 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0634. Min Act: -0.0002

Data Index: 79954 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0630. Min Act: -0.0002

Data Index: 226937 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0643. Min Act: -0.0002

Data Index: 848334 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0630. Min Act: -0.0002

Data Index: 471506 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0612. Min Act: -0.0002

Data Index: 151564 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1249665 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1227520 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0596. Min Act: -0.0002

Data Index: 120512 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0592. Min Act: -0.0002

Data Index: 786876 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1055310 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0579. Min Act: -0.0002

Data Index: 552858 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0586. Min Act: -0.0002

Data Index: 413503 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0593. Min Act: -0.0002

Data Index: 125737 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0583. Min Act: -0.0002

Data Index: 847864 (C4 (Web Text))

Max Activating Token Index: 451