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

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

Neuron 1626 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: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0001

Data Index: 807410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 261513 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1642447 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1592328 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1654363 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1486023 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1428365 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1642305 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1653651 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1452845 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1518692 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1420121 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 344755 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 344815 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 675640 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 464971 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 202053 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 163508 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 837977 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0122. Min Act: -0.0001

Data Index: 233697 (C4 (Web Text))

Max Activating Token Index: 1