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

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

Neuron 71 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1341749 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1184083 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1345976 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0593. Min Act: -0.0000

Data Index: 526363 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1456704 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0546. Min Act: -0.0001

Data Index: 262356 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1623908 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0540. Min Act: -0.0001

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0541. Min Act: -0.0001

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0500. Min Act: -0.0001

Data Index: 313520 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1189278 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0514. Min Act: -0.0001

Data Index: 476053 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1539031 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0496. Min Act: -0.0001

Data Index: 636154 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0530. Min Act: -0.0001

Data Index: 260502 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0472. Min Act: -0.0001

Data Index: 884699 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0468. Min Act: -0.0001

Data Index: 986111 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1448021 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1078920 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0480. Min Act: -0.0001

Data Index: 47241 (C4 (Web Text))

Max Activating Token Index: 25