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

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

Neuron 1612 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1646424 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1409249 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1556629 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1467606 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1455934 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0531. Min Act: -0.0001

Data Index: 249395 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0544. Min Act: -0.0001

Data Index: 605703 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0535. Min Act: -0.0001

Data Index: 691100 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1589738 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1570760 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0539. Min Act: -0.0001

Data Index: 901676 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1197630 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1594348 (Python Code)

Max Activating Token Index: 906

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1552800 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1518751 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1475758 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1453357 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0513. Min Act: -0.0001

Data Index: 343664 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1372745 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1547987 (Python Code)

Max Activating Token Index: 70