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

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

Neuron 1126 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: 3.8710. Min Range: -3.8710

Max Act: 3.8710. Min Act: -0.1699

Data Index: 1480014 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1584657 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7362. Min Act: -0.1700

Data Index: 1623770 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1375230 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.7159. Min Act: -0.1700

Data Index: 1383248 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6955. Min Act: -0.1700

Data Index: 1334313 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6608. Min Act: -0.1700

Data Index: 1652215 (Python Code)

Max Activating Token Index: 471

Text #7

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6151. Min Act: -0.1700

Data Index: 1391674 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1417823 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5996. Min Act: -0.1700

Data Index: 1581841 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5931. Min Act: -0.1700

Data Index: 1614949 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5861. Min Act: -0.1700

Data Index: 1616768 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5602. Min Act: -0.1700

Data Index: 1434328 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5590. Min Act: -0.1700

Data Index: 1364381 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1625986 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5473. Min Act: -0.1700

Data Index: 1641175 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5451. Min Act: -0.1699

Data Index: 1599851 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5503. Min Act: -0.1700

Data Index: 1372682 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5315. Min Act: -0.1699

Data Index: 1644140 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 3.8710. Min Range: -3.8710

Max Act: 3.5513. Min Act: -0.1700

Data Index: 1577187 (Python Code)

Max Activating Token Index: 271