Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 330 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.0498. Min Range: -7.0498

Max Act: 7.0498. Min Act: -0.1700

Data Index: 1078886 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.7060. Min Act: -0.1700

Data Index: 539141 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.6748. Min Act: -0.1700

Data Index: 953243 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.5185. Min Act: -0.1700

Data Index: 526866 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.5185. Min Act: -0.1700

Data Index: 762638 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.5498. Min Act: -0.1700

Data Index: 372224 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.4873. Min Act: -0.1699

Data Index: 423403 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3310. Min Act: -0.1700

Data Index: 401714 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3935. Min Act: -0.1700

Data Index: 81589 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.4873. Min Act: -0.1700

Data Index: 769332 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.4248. Min Act: -0.1700

Data Index: 683663 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3935. Min Act: -0.1700

Data Index: 1165715 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3623. Min Act: -0.1700

Data Index: 881169 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3623. Min Act: -0.1700

Data Index: 260135 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.2998. Min Act: -0.1700

Data Index: 541520 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3310. Min Act: -0.1700

Data Index: 440313 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3310. Min Act: -0.1700

Data Index: 1039489 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3310. Min Act: -0.1700

Data Index: 316244 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.2998. Min Act: -0.1700

Data Index: 1207586 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 7.0498. Min Range: -7.0498

Max Act: 6.3623. Min Act: -0.1700

Data Index: 827509 (C4 (Web Text))

Max Activating Token Index: 492