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

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

Neuron 75 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: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0006

Data Index: 893811 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0511. Min Act: -0.0006

Data Index: 210355 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0482. Min Act: -0.0006

Data Index: 5629 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0472. Min Act: -0.0006

Data Index: 861010 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0456. Min Act: -0.0006

Data Index: 598797 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0448. Min Act: -0.0006

Data Index: 308658 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0438. Min Act: -0.0006

Data Index: 897919 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0449. Min Act: -0.0006

Data Index: 332109 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0427. Min Act: -0.0006

Data Index: 351398 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1108800 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0426. Min Act: -0.0006

Data Index: 762791 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0426. Min Act: -0.0006

Data Index: 391887 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0423. Min Act: -0.0006

Data Index: 579561 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0413. Min Act: -0.0006

Data Index: 78899 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1173540 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0409. Min Act: -0.0006

Data Index: 53376 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1077120 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0404. Min Act: -0.0006

Data Index: 184284 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0413. Min Act: -0.0006

Data Index: 162003 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0398. Min Act: -0.0006

Data Index: 343910 (C4 (Web Text))

Max Activating Token Index: 192