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

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

Neuron 307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1287570 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9338. Min Act: -0.0000

Data Index: 446124 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8969. Min Act: -0.0000

Data Index: 533440 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8974. Min Act: -0.0000

Data Index: 761905 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9214. Min Act: -0.0000

Data Index: 552075 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9165. Min Act: -0.0000

Data Index: 62372 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1153747 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1099036 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8961. Min Act: -0.0000

Data Index: 241789 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1230197 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9053. Min Act: -0.0000

Data Index: 368718 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8702. Min Act: -0.0000

Data Index: 329654 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1161795 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8561. Min Act: -0.0000

Data Index: 730726 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8555. Min Act: -0.0000

Data Index: 918749 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8011. Min Act: -0.0000

Data Index: 550409 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7881. Min Act: -0.0000

Data Index: 485859 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7970. Min Act: -0.0000

Data Index: 860681 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1098424 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8040. Min Act: -0.0000

Data Index: 398855 (C4 (Web Text))

Max Activating Token Index: 243