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

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

Neuron 1282 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: 4.4391. Min Range: -4.4391

Max Act: 4.4391. Min Act: -0.1700

Data Index: 1644736 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.3412. Min Act: -0.1696

Data Index: 1642688 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.2563. Min Act: -0.1699

Data Index: 154970 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.2004. Min Act: -0.1700

Data Index: 746252 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.1603. Min Act: -0.1700

Data Index: 377585 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0720. Min Act: -0.1700

Data Index: 1597928 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0833. Min Act: -0.1700

Data Index: 1458135 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0563. Min Act: -0.1700

Data Index: 1451633 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0279. Min Act: -0.1700

Data Index: 825327 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0058. Min Act: -0.1698

Data Index: 1511837 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.0025. Min Act: -0.1700

Data Index: 320630 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9820. Min Act: -0.1691

Data Index: 1337153 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9893. Min Act: -0.1699

Data Index: 1535578 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9790. Min Act: -0.1700

Data Index: 1459716 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9814. Min Act: -0.1700

Data Index: 1536250 (Python Code)

Max Activating Token Index: 350

Text #15

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9606. Min Act: -0.1700

Data Index: 1485982 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9272. Min Act: -0.1700

Data Index: 1601458 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9496. Min Act: -0.1700

Data Index: 208645 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9480. Min Act: -0.1698

Data Index: 500679 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.9522. Min Act: -0.1700

Data Index: 1406554 (Python Code)

Max Activating Token Index: 191