Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2751. Min Act: -0.0001

Data Index: 492310 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1242014 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2140. Min Act: -0.0001

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1264656 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2219. Min Act: -0.0001

Data Index: 243590 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2166. Min Act: -0.0001

Data Index: 563485 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1197915 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2123. Min Act: -0.0001

Data Index: 1001120 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1964. Min Act: -0.0001

Data Index: 241386 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1950. Min Act: -0.0001

Data Index: 306346 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2141. Min Act: -0.0001

Data Index: 351297 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2196. Min Act: -0.0001

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1985. Min Act: -0.0001

Data Index: 795269 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1971. Min Act: -0.0001

Data Index: 174384 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2098. Min Act: -0.0001

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1945. Min Act: -0.0001

Data Index: 598514 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1926. Min Act: -0.0001

Data Index: 577948 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1916. Min Act: -0.0001

Data Index: 974979 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1725. Min Act: -0.0001

Data Index: 522100 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1275629 (C4 (Web Text))

Max Activating Token Index: 161