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

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

Neuron 1383 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: 15.4349. Min Range: -15.4349

Max Act: 15.4349. Min Act: -0.1700

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 15.4349. Min Range: -15.4349

Max Act: 15.3894. Min Act: -0.1700

Data Index: 1404851 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 15.4349. Min Range: -15.4349

Max Act: 15.2610. Min Act: -0.1700

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 15.4349. Min Range: -15.4349

Max Act: 15.2883. Min Act: -0.1700

Data Index: 1520583 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 15.4349. Min Range: -15.4349

Max Act: 15.1005. Min Act: -0.1700

Data Index: 1548149 (Python Code)

Max Activating Token Index: 537

Text #5

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.9571. Min Act: -0.1652

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.8050. Min Act: -0.1700

Data Index: 1592952 (Python Code)

Max Activating Token Index: 813

Text #7

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.8081. Min Act: -0.1699

Data Index: 1507974 (Python Code)

Max Activating Token Index: 375

Text #8

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.7233. Min Act: -0.1700

Data Index: 1436275 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.6258. Min Act: -0.1700

Data Index: 1460718 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.6183. Min Act: -0.1700

Data Index: 1363578 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.5046. Min Act: -0.1700

Data Index: 1388261 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.5205. Min Act: -0.1700

Data Index: 1629689 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.4645. Min Act: -0.1700

Data Index: 1566267 (Python Code)

Max Activating Token Index: 386

Text #14

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.3327. Min Act: -0.1700

Data Index: 1587263 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.4227. Min Act: -0.1700

Data Index: 1464254 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.4067. Min Act: -0.1700

Data Index: 1541679 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.3958. Min Act: -0.1699

Data Index: 427553 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.3269. Min Act: -0.1700

Data Index: 1434429 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 15.4349. Min Range: -15.4349

Max Act: 14.2790. Min Act: -0.1700

Data Index: 1416613 (Python Code)

Max Activating Token Index: 349