Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0490. Min Act: 0.0000

Data Index: 1557830 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0000

Data Index: 927298 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1655656 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0480. Min Act: 0.0003

Data Index: 1398187 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1542484 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0459. Min Act: -0.0000

Data Index: 58016 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1389039 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1614910 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0414. Min Act: 0.0000

Data Index: 1475344 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0378. Min Act: 0.0001

Data Index: 1173444 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0405. Min Act: 0.0000

Data Index: 1639201 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1548444 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1432517 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1476540 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0360. Min Act: 0.0001

Data Index: 1624025 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1471718 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1590478 (Python Code)

Max Activating Token Index: 143

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1555504 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1545879 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1456894 (Python Code)

Max Activating Token Index: 22