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

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

Neuron 3599 in Layer 1

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: 0.8574. Min Range: -0.8574

Max Act: 0.8574. Min Act: -0.0002

Data Index: 849078 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7294. Min Act: -0.0002

Data Index: 1523990 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.5007. Min Act: -0.0002

Data Index: 1560399 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4696. Min Act: -0.0002

Data Index: 1455819 (Python Code)

Max Activating Token Index: 900

Text #4

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4598. Min Act: -0.0002

Data Index: 1400787 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4590. Min Act: -0.0002

Data Index: 1525475 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4507. Min Act: -0.0002

Data Index: 1583393 (Python Code)

Max Activating Token Index: 302

Text #7

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4476. Min Act: -0.0002

Data Index: 1435901 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4597. Min Act: -0.0002

Data Index: 1542885 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4421. Min Act: -0.0002

Data Index: 1583064 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4491. Min Act: -0.0002

Data Index: 1526945 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4540. Min Act: -0.0002

Data Index: 1382230 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4351. Min Act: -0.0002

Data Index: 1402359 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4482. Min Act: -0.0002

Data Index: 1387697 (Python Code)

Max Activating Token Index: 840

Text #14

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4463. Min Act: -0.0002

Data Index: 1627371 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4343. Min Act: -0.0002

Data Index: 1598115 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4448. Min Act: -0.0002

Data Index: 1367133 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4383. Min Act: -0.0002

Data Index: 1404347 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4389. Min Act: -0.0002

Data Index: 1448240 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.4363. Min Act: -0.0002

Data Index: 1388044 (Python Code)

Max Activating Token Index: 763