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

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

Neuron 1036 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: 0.0043. Min Range: -0.0043

Max Act: 0.0043. Min Act: -0.0002

Data Index: 841048 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0040. Min Act: -0.0002

Data Index: 511065 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0039. Min Act: -0.0001

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0001

Data Index: 319695 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0002

Data Index: 288613 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0038. Min Act: -0.0002

Data Index: 60588 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0037. Min Act: -0.0001

Data Index: 1276574 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 1422578 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 1426547 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 383346 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 1592170 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0001

Data Index: 249039 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 960936 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0001

Data Index: 1452133 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0002

Data Index: 592311 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0001

Data Index: 1300540 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0036. Min Act: -0.0001

Data Index: 1499048 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0001

Data Index: 1568726 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0034. Min Act: -0.0001

Data Index: 1593208 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0043. Min Range: -0.0043

Max Act: 0.0035. Min Act: -0.0001

Data Index: 1515580 (Python Code)

Max Activating Token Index: 1023