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

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

Neuron 1232 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: 6.2626. Min Range: -6.2626

Max Act: 6.2626. Min Act: -0.1700

Data Index: 1190990 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 6.2626. Min Range: -6.2626

Max Act: 6.0751. Min Act: -0.1684

Data Index: 881075 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 6.2626. Min Range: -6.2626

Max Act: 6.0439. Min Act: -0.1700

Data Index: 418271 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.9814. Min Act: -0.1699

Data Index: 986557 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.8876. Min Act: -0.1700

Data Index: 1108829 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.9189. Min Act: -0.1700

Data Index: 792160 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.8564. Min Act: -0.1700

Data Index: 809756 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.8564. Min Act: -0.1700

Data Index: 683647 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.8564. Min Act: -0.1700

Data Index: 548667 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.7939. Min Act: -0.1700

Data Index: 444762 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.7314. Min Act: -0.1699

Data Index: 80023 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.7626. Min Act: -0.1699

Data Index: 523839 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.7939. Min Act: -0.1700

Data Index: 606808 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6689. Min Act: -0.1699

Data Index: 616195 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.7314. Min Act: -0.1700

Data Index: 889831 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6689. Min Act: -0.1699

Data Index: 86545 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6689. Min Act: -0.1700

Data Index: 1334676 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6689. Min Act: -0.1697

Data Index: 701642 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6376. Min Act: -0.1700

Data Index: 844838 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 6.2626. Min Range: -6.2626

Max Act: 5.6064. Min Act: -0.1700

Data Index: 157486 (C4 (Web Text))

Max Activating Token Index: 342