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

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

Neuron 802 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0414. Min Act: -0.0002

Data Index: 111610 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0001

Data Index: 87153 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0392. Min Act: -0.0002

Data Index: 29223 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0366. Min Act: -0.0002

Data Index: 195826 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0374. Min Act: -0.0002

Data Index: 611534 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0367. Min Act: -0.0002

Data Index: 474486 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0374. Min Act: -0.0002

Data Index: 563297 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0350. Min Act: -0.0002

Data Index: 286537 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1354731 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0351. Min Act: -0.0001

Data Index: 824537 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0354. Min Act: -0.0002

Data Index: 586201 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0338. Min Act: -0.0002

Data Index: 335867 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1559437 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0340. Min Act: -0.0002

Data Index: 437074 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0328. Min Act: -0.0002

Data Index: 690182 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0337. Min Act: -0.0002

Data Index: 503894 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0341. Min Act: -0.0002

Data Index: 505937 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1502362 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0324. Min Act: -0.0002

Data Index: 871794 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0336. Min Act: -0.0002

Data Index: 798665 (C4 (Web Text))

Max Activating Token Index: 85