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

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

Neuron 1445 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: 0.4659. Min Range: -0.4659

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1379415 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1515379 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1524664 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1479589 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4375. Min Act: -0.0001

Data Index: 1567419 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1592263 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1535155 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1388319 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4195. Min Act: -0.0001

Data Index: 827050 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1525790 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1496919 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1483510 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1492189 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4069. Min Act: -0.0001

Data Index: 1535663 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4120. Min Act: -0.0001

Data Index: 1572304 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1492117 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1360480 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1607433 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1429108 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4022. Min Act: -0.0001

Data Index: 1489698 (Python Code)

Max Activating Token Index: 1023