Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1723 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0661. Min Act: -0.0001

Data Index: 640076 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0001

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1514353 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0559. Min Act: -0.0001

Data Index: 12433 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0540. Min Act: -0.0001

Data Index: 997511 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1506476 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0582. Min Act: -0.0001

Data Index: 130879 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0583. Min Act: -0.0001

Data Index: 297088 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0551. Min Act: -0.0001

Data Index: 612236 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1271669 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0515. Min Act: -0.0001

Data Index: 10519 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0554. Min Act: -0.0001

Data Index: 710687 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1207747 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1632302 (Python Code)

Max Activating Token Index: 612

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1635266 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0487. Min Act: -0.0001

Data Index: 479131 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0531. Min Act: -0.0001

Data Index: 62104 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0549. Min Act: -0.0001

Data Index: 358251 (C4 (Web Text))

Max Activating Token Index: 680