Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0000

Data Index: 952716 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1353605 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0001

Data Index: 827853 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1430300 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0656. Min Act: -0.0001

Data Index: 326056 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0631. Min Act: -0.0001

Data Index: 849426 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0669. Min Act: -0.0001

Data Index: 261843 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0616. Min Act: -0.0001

Data Index: 826400 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0573. Min Act: -0.0001

Data Index: 393437 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0580. Min Act: -0.0000

Data Index: 311440 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0583. Min Act: -0.0001

Data Index: 456920 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1004924 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1209227 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1480825 (Python Code)

Max Activating Token Index: 780

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0566. Min Act: -0.0000

Data Index: 335756 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1112430 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1319695 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1245789 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0595. Min Act: -0.0001

Data Index: 63192 (C4 (Web Text))

Max Activating Token Index: 84