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

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

Neuron 3757 in Layer 0

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: 0.6284. Min Range: -0.6284

Max Act: 0.6284. Min Act: -0.0001

Data Index: 716467 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.6026. Min Act: -0.0001

Data Index: 301908 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.6067. Min Act: -0.0001

Data Index: 33465 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.6044. Min Act: -0.0001

Data Index: 151880 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5933. Min Act: -0.0001

Data Index: 949413 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1088485 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5788. Min Act: -0.0001

Data Index: 747997 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5654. Min Act: -0.0001

Data Index: 293725 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1055386 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1127015 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5660. Min Act: -0.0001

Data Index: 1039960 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5645. Min Act: -0.0001

Data Index: 654098 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5666. Min Act: -0.0001

Data Index: 316907 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5566. Min Act: -0.0001

Data Index: 901445 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5431. Min Act: -0.0001

Data Index: 752868 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5585. Min Act: -0.0001

Data Index: 13278 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5557. Min Act: -0.0001

Data Index: 963455 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5490. Min Act: -0.0001

Data Index: 53377 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5660. Min Act: -0.0001

Data Index: 395776 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.6284. Min Range: -0.6284

Max Act: 0.5526. Min Act: -0.0001

Data Index: 483150 (C4 (Web Text))

Max Activating Token Index: 809