Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 718 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0006

Data Index: 903126 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0525. Min Act: -0.0006

Data Index: 503413 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1084281 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0451. Min Act: -0.0006

Data Index: 680672 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0480. Min Act: -0.0006

Data Index: 998462 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1353208 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0471. Min Act: -0.0006

Data Index: 872379 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0443. Min Act: -0.0006

Data Index: 1298264 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0476. Min Act: -0.0006

Data Index: 328028 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0436. Min Act: -0.0006

Data Index: 762754 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0441. Min Act: -0.0006

Data Index: 697099 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0447. Min Act: -0.0006

Data Index: 178724 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0421. Min Act: -0.0006

Data Index: 9727 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0420. Min Act: -0.0006

Data Index: 519175 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0437. Min Act: -0.0006

Data Index: 269053 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0432. Min Act: -0.0006

Data Index: 625354 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0424. Min Act: -0.0006

Data Index: 785612 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0443. Min Act: -0.0006

Data Index: 168326 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0414. Min Act: -0.0006

Data Index: 143548 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0411. Min Act: -0.0006

Data Index: 260440 (C4 (Web Text))

Max Activating Token Index: 633