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

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

Neuron 2598 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: 0.0236. Min Range: -0.0236

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1535682 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0150. Min Act: -0.0002

Data Index: 365625 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1374433 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1648198 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1544577 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1394443 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1497890 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1581865 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1517657 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1642288 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1533632 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1288563 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1605439 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1644863 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1426087 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0116. Min Act: -0.0002

Data Index: 246533 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1418709 (Python Code)

Max Activating Token Index: 836

Text #17

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1435518 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1453039 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.0236. Min Range: -0.0236

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1159684 (C4 (Web Text))

Max Activating Token Index: 212