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

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

Neuron 182 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: 7.4367. Min Range: -7.4367

Max Act: 7.4367. Min Act: -0.1700

Data Index: 1140899 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 7.4367. Min Range: -7.4367

Max Act: 7.1469. Min Act: -0.1670

Data Index: 1364994 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 7.4367. Min Range: -7.4367

Max Act: 7.0429. Min Act: -0.1700

Data Index: 51568 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 7.4367. Min Range: -7.4367

Max Act: 7.0060. Min Act: -0.1700

Data Index: 546627 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.7325. Min Act: -0.1698

Data Index: 1505853 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.5352. Min Act: -0.1700

Data Index: 928346 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.4174. Min Act: -0.1700

Data Index: 315798 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.3931. Min Act: -0.1700

Data Index: 844559 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.3788. Min Act: -0.1699

Data Index: 1477291 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.3771. Min Act: -0.1700

Data Index: 651590 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.2899. Min Act: -0.1700

Data Index: 1654767 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.2826. Min Act: -0.1700

Data Index: 1414603 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.2310. Min Act: -0.1700

Data Index: 1641978 (Python Code)

Max Activating Token Index: 181

Text #13

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.1040. Min Act: -0.1700

Data Index: 1656373 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.0848. Min Act: -0.1700

Data Index: 1547000 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.0759. Min Act: -0.1700

Data Index: 1453203 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.0588. Min Act: -0.1700

Data Index: 1616274 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 7.4367. Min Range: -7.4367

Max Act: 6.0479. Min Act: -0.1700

Data Index: 1532060 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 7.4367. Min Range: -7.4367

Max Act: 5.9464. Min Act: -0.1700

Data Index: 1451327 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 7.4367. Min Range: -7.4367

Max Act: 5.8915. Min Act: -0.1699

Data Index: 1641838 (Python Code)

Max Activating Token Index: 627