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

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

Neuron 826 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: 3.4505. Min Range: -3.4505

Max Act: 3.4505. Min Act: -0.1699

Data Index: 1469738 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.3977. Min Act: -0.1700

Data Index: 1562651 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.3460. Min Act: -0.1699

Data Index: 1635204 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.3282. Min Act: -0.1700

Data Index: 1420659 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.3117. Min Act: -0.1624

Data Index: 1601800 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2944. Min Act: -0.1670

Data Index: 1624226 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2559. Min Act: -0.1694

Data Index: 1620786 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2298. Min Act: -0.1699

Data Index: 1573023 (Python Code)

Max Activating Token Index: 953

Text #8

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2458. Min Act: -0.1640

Data Index: 1591692 (Python Code)

Max Activating Token Index: 697

Text #9

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2343. Min Act: -0.1699

Data Index: 1447730 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1506591 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2287. Min Act: -0.1700

Data Index: 1498415 (Python Code)

Max Activating Token Index: 201

Text #12

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2277. Min Act: -0.1697

Data Index: 1402985 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2308. Min Act: -0.1699

Data Index: 1543115 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1983. Min Act: -0.1700

Data Index: 1618691 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.2144. Min Act: -0.1700

Data Index: 1413979 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1595. Min Act: -0.1700

Data Index: 1604591 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1909. Min Act: -0.1699

Data Index: 1611790 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1910. Min Act: -0.1699

Data Index: 1558869 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.1813. Min Act: -0.1700

Data Index: 1547879 (Python Code)

Max Activating Token Index: 640