Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4461 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.2444. Min Act: -0.0000

Data Index: 548569 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.4436. Min Act: -0.0000

Data Index: 1169374 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.3172. Min Act: -0.0000

Data Index: 569804 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1482038 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1596868 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1490042 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1600575 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9227. Min Act: -0.0000

Data Index: 381204 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1557767 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1558547 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0546. Min Act: -0.0000

Data Index: 654578 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1248063 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9153. Min Act: -0.0000

Data Index: 180731 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1533381 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1635256 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1518960 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1493590 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1571239 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1652775 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1052207 (C4 (Web Text))

Max Activating Token Index: 427