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

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

Neuron 3684 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1480858 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1408270 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1592893 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1490120 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1361362 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1637224 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1431685 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1606285 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1389645 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1378518 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1502115 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1455851 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1396172 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1647725 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1478160 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1612791 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1640737 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1382746 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1571882 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1634658 (Python Code)

Max Activating Token Index: 147