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

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

Neuron 4960 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: 1.6378. Min Range: -1.6378

Max Act: 1.6378. Min Act: -0.0002

Data Index: 955498 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.6284. Min Act: -0.0002

Data Index: 144429 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5936. Min Act: -0.0002

Data Index: 849687 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5637. Min Act: -0.0002

Data Index: 689215 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5378. Min Act: -0.0002

Data Index: 543772 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5448. Min Act: -0.0002

Data Index: 1257391 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5292. Min Act: -0.0002

Data Index: 340361 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5268. Min Act: -0.0002

Data Index: 311928 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5138. Min Act: -0.0002

Data Index: 985777 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4946. Min Act: -0.0002

Data Index: 578202 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4751. Min Act: -0.0002

Data Index: 941359 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.5121. Min Act: -0.0002

Data Index: 379538 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4879. Min Act: -0.0002

Data Index: 755710 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4893. Min Act: -0.0002

Data Index: 635864 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4668. Min Act: -0.0002

Data Index: 533458 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4560. Min Act: -0.0002

Data Index: 161382 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4704. Min Act: -0.0002

Data Index: 399158 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4555. Min Act: -0.0002

Data Index: 1004200 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4557. Min Act: -0.0002

Data Index: 8990 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.6378. Min Range: -1.6378

Max Act: 1.4583. Min Act: -0.0002

Data Index: 21554 (C4 (Web Text))

Max Activating Token Index: 682