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

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

Neuron 1571 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: 5.0523. Min Range: -5.0523

Max Act: 5.0523. Min Act: -0.1525

Data Index: 546627 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 5.0523. Min Range: -5.0523

Max Act: 5.0147. Min Act: -0.1697

Data Index: 1140899 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7860. Min Act: -0.1700

Data Index: 928346 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7268. Min Act: -0.1694

Data Index: 51568 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.7128. Min Act: -0.1700

Data Index: 1414603 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6978. Min Act: -0.1700

Data Index: 651590 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.6121. Min Act: -0.1700

Data Index: 403079 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.5594. Min Act: -0.1699

Data Index: 1641978 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.5660. Min Act: -0.1700

Data Index: 1576909 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.5018. Min Act: -0.1700

Data Index: 1656373 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.4452. Min Act: -0.1700

Data Index: 844559 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.3919. Min Act: -0.1700

Data Index: 205958 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.3979. Min Act: -0.1699

Data Index: 1411884 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.3632. Min Act: -0.1697

Data Index: 1504954 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.3194. Min Act: -0.1694

Data Index: 138586 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.2765. Min Act: -0.1700

Data Index: 1406721 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.2563. Min Act: -0.1699

Data Index: 1473501 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.2365. Min Act: -0.1700

Data Index: 1403007 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.2227. Min Act: -0.1700

Data Index: 1488478 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 5.0523. Min Range: -5.0523

Max Act: 4.2002. Min Act: -0.1700

Data Index: 1439901 (Python Code)

Max Activating Token Index: 239