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

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

Neuron 1025 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: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0002

Data Index: 36016 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1109390 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0419. Min Act: -0.0002

Data Index: 107163 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0414. Min Act: -0.0002

Data Index: 474002 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0418. Min Act: -0.0002

Data Index: 742917 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0408. Min Act: -0.0002

Data Index: 436911 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0401. Min Act: -0.0002

Data Index: 950854 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0402. Min Act: -0.0002

Data Index: 387391 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1115614 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0384. Min Act: -0.0002

Data Index: 546980 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0389. Min Act: -0.0002

Data Index: 359466 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0385. Min Act: -0.0002

Data Index: 6544 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0389. Min Act: -0.0002

Data Index: 289246 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0367. Min Act: -0.0002

Data Index: 868432 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0362. Min Act: -0.0002

Data Index: 31206 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1335532 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1051999 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0377. Min Act: -0.0002

Data Index: 638042 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0360. Min Act: -0.0002

Data Index: 566304 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0374. Min Act: -0.0002

Data Index: 969091 (C4 (Web Text))

Max Activating Token Index: 862