Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1646. Min Range: -4.1646

Max Act: 4.1646. Min Act: -0.1700

Data Index: 1272943 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 4.1646. Min Range: -4.1646

Max Act: 4.0708. Min Act: -0.1700

Data Index: 138385 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.8832. Min Act: -0.1700

Data Index: 1054802 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.8520. Min Act: -0.1700

Data Index: 942374 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.8050. Min Act: -0.1700

Data Index: 238654 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.8363. Min Act: -0.1700

Data Index: 1020182 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7581. Min Act: -0.1700

Data Index: 537980 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7581. Min Act: -0.1700

Data Index: 1292868 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7268. Min Act: -0.1700

Data Index: 371037 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7268. Min Act: -0.1700

Data Index: 503770 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7425. Min Act: -0.1700

Data Index: 1259218 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7268. Min Act: -0.1700

Data Index: 1009150 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7268. Min Act: -0.1700

Data Index: 981791 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.6955. Min Act: -0.1700

Data Index: 91513 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7268. Min Act: -0.1700

Data Index: 504363 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7112. Min Act: -0.1700

Data Index: 415820 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.6799. Min Act: -0.1700

Data Index: 484205 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.6329. Min Act: -0.1700

Data Index: 735699 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.7112. Min Act: -0.1700

Data Index: 364748 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 4.1646. Min Range: -4.1646

Max Act: 3.6642. Min Act: -0.1700

Data Index: 919206 (C4 (Web Text))

Max Activating Token Index: 635