Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0470. Min Act: -0.0003

Data Index: 611719 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1639730 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1274575 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0506. Min Act: -0.0003

Data Index: 94354 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0475. Min Act: -0.0003

Data Index: 295392 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1445312 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0503. Min Act: -0.0003

Data Index: 522785 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0481. Min Act: -0.0003

Data Index: 88747 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0469. Min Act: -0.0003

Data Index: 807740 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1222017 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1592275 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0404. Min Act: -0.0003

Data Index: 595069 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1160450 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0446. Min Act: -0.0003

Data Index: 370527 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0463. Min Act: -0.0003

Data Index: 547532 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1596638 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0405. Min Act: -0.0003

Data Index: 464397 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0417. Min Act: -0.0003

Data Index: 736043 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0401. Min Act: -0.0003

Data Index: 275320 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0489. Min Act: -0.0003

Data Index: 203117 (C4 (Web Text))

Max Activating Token Index: 992