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

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

Neuron 1374 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: 5.6639. Min Range: -5.6639

Max Act: 5.6639. Min Act: -0.1700

Data Index: 49972 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.6639. Min Act: -0.1700

Data Index: 381920 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.5701. Min Act: -0.1700

Data Index: 740989 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.5701. Min Act: -0.1700

Data Index: 487467 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.4451. Min Act: -0.1700

Data Index: 735052 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.4451. Min Act: -0.1699

Data Index: 639158 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.4451. Min Act: -0.1700

Data Index: 609359 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.4451. Min Act: -0.1700

Data Index: 1185307 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3201. Min Act: -0.1700

Data Index: 753359 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3826. Min Act: -0.1700

Data Index: 222880 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3201. Min Act: -0.1700

Data Index: 925118 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3514. Min Act: -0.1700

Data Index: 376946 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3514. Min Act: -0.1700

Data Index: 909113 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3514. Min Act: -0.1698

Data Index: 27782 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3201. Min Act: -0.1700

Data Index: 632998 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3514. Min Act: -0.1700

Data Index: 1111829 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.2889. Min Act: -0.1699

Data Index: 1032235 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.2576. Min Act: -0.1700

Data Index: 244417 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.2576. Min Act: -0.1700

Data Index: 208610 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.2889. Min Act: -0.1663

Data Index: 1305193 (C4 (Web Text))

Max Activating Token Index: 563