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

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

Neuron 1154 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: 5.8784. Min Range: -5.8784

Max Act: 5.8784. Min Act: -0.1700

Data Index: 57874 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6597. Min Act: -0.1700

Data Index: 932078 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 315423 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 869598 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5659. Min Act: -0.1699

Data Index: 514720 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4722. Min Act: -0.1700

Data Index: 158861 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4566. Min Act: -0.1700

Data Index: 788413 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4409. Min Act: -0.1700

Data Index: 36022 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4566. Min Act: -0.1700

Data Index: 859597 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4566. Min Act: -0.1700

Data Index: 1019378 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4253. Min Act: -0.1700

Data Index: 1266778 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4409. Min Act: -0.1700

Data Index: 1207865 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4097. Min Act: -0.1700

Data Index: 652486 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4097. Min Act: -0.1700

Data Index: 275926 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4097. Min Act: -0.1700

Data Index: 974343 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4253. Min Act: -0.1700

Data Index: 381646 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.3784. Min Act: -0.1700

Data Index: 238393 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.3784. Min Act: -0.1700

Data Index: 842235 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4097. Min Act: -0.1700

Data Index: 1078260 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.3628. Min Act: -0.1700

Data Index: 73229 (C4 (Web Text))

Max Activating Token Index: 352