Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2868 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1085361 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1302051 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0001

Data Index: 320010 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0477. Min Act: -0.0002

Data Index: 247822 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1173672 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0002

Data Index: 311277 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0475. Min Act: -0.0002

Data Index: 33748 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0426. Min Act: -0.0001

Data Index: 185675 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0002

Data Index: 630785 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1122861 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0441. Min Act: -0.0001

Data Index: 109083 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0447. Min Act: -0.0001

Data Index: 349065 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0428. Min Act: -0.0001

Data Index: 632592 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0439. Min Act: -0.0001

Data Index: 435601 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0412. Min Act: -0.0001

Data Index: 60414 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0429. Min Act: -0.0002

Data Index: 35544 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0413. Min Act: -0.0001

Data Index: 661929 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0418. Min Act: -0.0002

Data Index: 151402 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1078844 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0408. Min Act: -0.0002

Data Index: 24727 (C4 (Web Text))

Max Activating Token Index: 532