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

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

Neuron 518 in Layer 1

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: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0002

Data Index: 144145 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3172. Min Act: -0.0002

Data Index: 780401 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2715. Min Act: -0.0002

Data Index: 1310270 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2680. Min Act: -0.0002

Data Index: 522857 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2674. Min Act: -0.0002

Data Index: 296805 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2618. Min Act: -0.0003

Data Index: 387115 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2636. Min Act: -0.0002

Data Index: 154701 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2647. Min Act: -0.0002

Data Index: 279200 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2564. Min Act: -0.0002

Data Index: 829589 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2583. Min Act: -0.0002

Data Index: 1187610 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2648. Min Act: -0.0002

Data Index: 365510 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2573. Min Act: -0.0002

Data Index: 713473 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2557. Min Act: -0.0002

Data Index: 1130712 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2478. Min Act: -0.0002

Data Index: 201901 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2531. Min Act: -0.0002

Data Index: 24443 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2512. Min Act: -0.0002

Data Index: 6273 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2516. Min Act: -0.0002

Data Index: 522071 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2493. Min Act: -0.0002

Data Index: 504748 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2394. Min Act: -0.0002

Data Index: 279966 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2405. Min Act: -0.0002

Data Index: 1012173 (C4 (Web Text))

Max Activating Token Index: 746