Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1235 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0397. Min Act: -0.0006

Data Index: 70823 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0398. Min Act: -0.0006

Data Index: 270422 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1172977 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0389. Min Act: -0.0006

Data Index: 276134 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0395. Min Act: -0.0006

Data Index: 610006 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0369. Min Act: -0.0006

Data Index: 1226077 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0437. Min Act: -0.0006

Data Index: 1201216 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0006

Data Index: 788115 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0388. Min Act: -0.0006

Data Index: 69950 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0391. Min Act: -0.0006

Data Index: 599782 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1042168 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0374. Min Act: -0.0006

Data Index: 967444 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0368. Min Act: -0.0006

Data Index: 425950 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0372. Min Act: -0.0006

Data Index: 452247 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0362. Min Act: -0.0006

Data Index: 357653 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0381. Min Act: -0.0006

Data Index: 339256 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1051905 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0378. Min Act: -0.0006

Data Index: 604604 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0369. Min Act: -0.0006

Data Index: 638455 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0369. Min Act: -0.0006

Data Index: 632009 (C4 (Web Text))

Max Activating Token Index: 620