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

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

Neuron 4701 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: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1292567 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1160434 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0345. Min Act: -0.0001

Data Index: 967052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1107412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1475270 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0319. Min Act: -0.0001

Data Index: 462458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0319. Min Act: -0.0001

Data Index: 442727 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0322. Min Act: -0.0001

Data Index: 508144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1484675 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1641509 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0316. Min Act: -0.0001

Data Index: 445581 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0313. Min Act: -0.0001

Data Index: 915503 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0315. Min Act: -0.0001

Data Index: 973766 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0312. Min Act: -0.0001

Data Index: 349814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0319. Min Act: -0.0001

Data Index: 415508 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1395910 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1633591 (Python Code)

Max Activating Token Index: 729

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1581644 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1535144 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1481647 (Python Code)

Max Activating Token Index: 218