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

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

Neuron 5069 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: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1420356 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1563782 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1579492 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0001

Data Index: 1646875 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1370633 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1560262 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1544350 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1524581 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1378652 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0117. Min Act: -0.0001

Data Index: 1394595 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1574597 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1533582 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1487653 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1625311 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1400159 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1647874 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0001

Data Index: 1646172 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0001

Data Index: 1541503 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1597850 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1400841 (Python Code)

Max Activating Token Index: 17