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

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

Neuron 785 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: 5.1383. Min Range: -5.1383

Max Act: 5.1383. Min Act: -0.1700

Data Index: 516988 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.7008. Min Act: -0.1700

Data Index: 223542 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.6695. Min Act: -0.1700

Data Index: 1353066 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.6070. Min Act: -0.1700

Data Index: 1318546 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.6070. Min Act: -0.1700

Data Index: 146431 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5758. Min Act: -0.1683

Data Index: 951551 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5758. Min Act: -0.1700

Data Index: 252372 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5758. Min Act: -0.1700

Data Index: 658219 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.6070. Min Act: -0.1700

Data Index: 864755 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5758. Min Act: -0.1700

Data Index: 760716 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5133. Min Act: -0.1700

Data Index: 1046464 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 1028849 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5133. Min Act: -0.1700

Data Index: 1043877 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 221890 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.5445. Min Act: -0.1699

Data Index: 1202631 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 667315 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 936448 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 1351589 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4820. Min Act: -0.1700

Data Index: 464565 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.4195. Min Act: -0.1700

Data Index: 737304 (C4 (Web Text))

Max Activating Token Index: 88