Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1637 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0006

Data Index: 508007 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0566. Min Act: -0.0006

Data Index: 1307012 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0553. Min Act: -0.0006

Data Index: 829280 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0540. Min Act: -0.0005

Data Index: 433850 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0498. Min Act: -0.0006

Data Index: 735442 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1225597 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1330545 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0496. Min Act: -0.0006

Data Index: 264180 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0497. Min Act: -0.0006

Data Index: 853867 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0503. Min Act: -0.0006

Data Index: 917482 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1113779 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0482. Min Act: -0.0006

Data Index: 559144 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0485. Min Act: -0.0006

Data Index: 381992 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0483. Min Act: -0.0005

Data Index: 879628 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0492. Min Act: -0.0006

Data Index: 35425 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1038197 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0489. Min Act: -0.0006

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1245538 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0486. Min Act: -0.0006

Data Index: 744327 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0470. Min Act: -0.0006

Data Index: 798122 (C4 (Web Text))

Max Activating Token Index: 310