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

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

Neuron 3789 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1204416 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0125. Min Act: -0.0001

Data Index: 747635 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0001

Data Index: 76212 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0123. Min Act: -0.0001

Data Index: 371429 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0001

Data Index: 309501 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0001

Data Index: 526762 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0123. Min Act: -0.0001

Data Index: 476738 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0001

Data Index: 733487 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1259358 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0001

Data Index: 862604 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0001

Data Index: 904182 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1572933 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1013270 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 24226 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1094399 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1096711 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 214370 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 975349 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 109310 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0001

Data Index: 688446 (C4 (Web Text))

Max Activating Token Index: 1