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

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

Neuron 4410 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: 1.0095. Min Range: -1.0095

Max Act: 1.0095. Min Act: -0.0002

Data Index: 334774 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9484. Min Act: -0.0002

Data Index: 793442 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9060. Min Act: -0.0002

Data Index: 1351297 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8727. Min Act: -0.0002

Data Index: 91002 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8533. Min Act: -0.0002

Data Index: 502561 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8516. Min Act: -0.0002

Data Index: 1144359 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8444. Min Act: -0.0002

Data Index: 693102 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7982. Min Act: -0.0002

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7969. Min Act: -0.0003

Data Index: 367892 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7856. Min Act: -0.0002

Data Index: 69987 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7699. Min Act: -0.0002

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7803. Min Act: -0.0002

Data Index: 1130384 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7718. Min Act: -0.0002

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7505. Min Act: -0.0002

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7535. Min Act: -0.0002

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7520. Min Act: -0.0002

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7597. Min Act: -0.0002

Data Index: 722007 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7483. Min Act: -0.0002

Data Index: 1277997 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7437. Min Act: -0.0002

Data Index: 455687 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7384. Min Act: -0.0002

Data Index: 26394 (C4 (Web Text))

Max Activating Token Index: 78