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

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

Neuron 1709 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: 3.1893. Min Range: -3.1893

Max Act: 3.1594. Min Act: -0.1699

Data Index: 215650 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1655815 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1721. Min Act: -0.1700

Data Index: 1020363 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1893. Min Act: -0.1700

Data Index: 501172 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1227. Min Act: -0.1700

Data Index: 765156 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1401. Min Act: -0.1700

Data Index: 1408483 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1195. Min Act: -0.1700

Data Index: 1581898 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1277. Min Act: -0.1700

Data Index: 1524951 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1559. Min Act: -0.1700

Data Index: 654096 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1476. Min Act: -0.1700

Data Index: 1136068 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1152. Min Act: -0.1700

Data Index: 1411867 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1049. Min Act: -0.1700

Data Index: 1166848 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1139. Min Act: -0.1700

Data Index: 628176 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0692. Min Act: -0.1700

Data Index: 1071110 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0751. Min Act: -0.1700

Data Index: 1366364 (Python Code)

Max Activating Token Index: 275

Text #15

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0743. Min Act: -0.1700

Data Index: 1444502 (Python Code)

Max Activating Token Index: 540

Text #16

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0769. Min Act: -0.1700

Data Index: 951428 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0656. Min Act: -0.1700

Data Index: 353374 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0797. Min Act: -0.1700

Data Index: 85681 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.0649. Min Act: -0.1700

Data Index: 643589 (C4 (Web Text))

Max Activating Token Index: 540