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

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

Neuron 2758 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: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1410600 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1488096 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1598588 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1608123 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1604778 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1557238 (Python Code)

Max Activating Token Index: 529

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1514021 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1491226 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1494643 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1607835 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1548968 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1367216 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1425950 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1520361 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1593132 (Python Code)

Max Activating Token Index: 334

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1480563 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1364032 (Python Code)

Max Activating Token Index: 993

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1539270 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1458445 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1627128 (Python Code)

Max Activating Token Index: 747