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

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

Neuron 3421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0000

Data Index: 386653 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0666. Min Act: -0.0001

Data Index: 973110 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1246948 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0545. Min Act: -0.0001

Data Index: 828641 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0561. Min Act: -0.0001

Data Index: 873991 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0527. Min Act: -0.0001

Data Index: 541709 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0506. Min Act: -0.0000

Data Index: 323079 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1176620 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1136372 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0507. Min Act: -0.0000

Data Index: 122817 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1163544 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0531. Min Act: -0.0000

Data Index: 995152 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0542. Min Act: -0.0001

Data Index: 185834 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0472. Min Act: -0.0000

Data Index: 463796 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0469. Min Act: -0.0000

Data Index: 603560 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0461. Min Act: -0.0001

Data Index: 386922 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1148472 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0483. Min Act: -0.0001

Data Index: 347561 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0468. Min Act: -0.0001

Data Index: 222489 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0441. Min Act: -0.0000

Data Index: 384449 (C4 (Web Text))

Max Activating Token Index: 972