Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1198 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1300. Min Range: -3.1300

Max Act: 3.1276. Min Act: -0.0236

Data Index: 1337642 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.1300. Min Range: -3.1300

Max Act: 3.1300. Min Act: -0.1700

Data Index: 1494814 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 3.1300. Min Range: -3.1300

Max Act: 3.0837. Min Act: -0.1700

Data Index: 1339149 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 3.1300. Min Range: -3.1300

Max Act: 3.0298. Min Act: -0.1700

Data Index: 385789 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9564. Min Act: -0.1601

Data Index: 1287859 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9578. Min Act: -0.1700

Data Index: 105162 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9692. Min Act: -0.1699

Data Index: 1173895 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9514. Min Act: -0.1700

Data Index: 1431404 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9608. Min Act: -0.1700

Data Index: 164686 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9432. Min Act: -0.1700

Data Index: 839201 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9537. Min Act: -0.1629

Data Index: 1313420 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9370. Min Act: -0.1695

Data Index: 138536 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9352. Min Act: -0.1690

Data Index: 854272 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.9330. Min Act: -0.1700

Data Index: 1290503 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8983. Min Act: -0.1585

Data Index: 378682 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8706. Min Act: -0.1700

Data Index: 288759 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8664. Min Act: -0.1700

Data Index: 1009690 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8742. Min Act: -0.1700

Data Index: 189104 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8558. Min Act: -0.1700

Data Index: 505422 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.1300. Min Range: -3.1300

Max Act: 2.8562. Min Act: -0.1700

Data Index: 1129359 (C4 (Web Text))

Max Activating Token Index: 628