Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0000

Data Index: 751529 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0604. Min Act: -0.0000

Data Index: 988232 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1491462 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1178936 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1514279 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0511. Min Act: -0.0000

Data Index: 38363 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0433. Min Act: -0.0000

Data Index: 573295 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0520. Min Act: -0.0000

Data Index: 629471 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1354049 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0441. Min Act: -0.0000

Data Index: 49711 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0489. Min Act: -0.0000

Data Index: 398266 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0493. Min Act: -0.0000

Data Index: 226964 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1460184 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0471. Min Act: -0.0000

Data Index: 578337 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0451. Min Act: -0.0000

Data Index: 387920 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0472. Min Act: -0.0000

Data Index: 326718 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0440. Min Act: -0.0000

Data Index: 516703 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1320469 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1154528 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0430. Min Act: -0.0000

Data Index: 941144 (C4 (Web Text))

Max Activating Token Index: 81