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

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

Neuron 1208 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.2155. Min Act: -0.1700

Data Index: 1090760 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1997. Min Act: -0.1700

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.2155. Min Act: -0.1700

Data Index: 21254 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1997. Min Act: -0.1700

Data Index: 361403 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1683. Min Act: -0.1700

Data Index: 284000 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1840. Min Act: -0.1700

Data Index: 721391 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1683. Min Act: -0.1700

Data Index: 932185 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1683. Min Act: -0.1700

Data Index: 466017 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1840. Min Act: -0.1700

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1525. Min Act: -0.1700

Data Index: 152877 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1028767 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1156344 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1683. Min Act: -0.1700

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1072086 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1368. Min Act: -0.1700

Data Index: 1454069 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1368. Min Act: -0.1700

Data Index: 340565 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1368. Min Act: -0.1700

Data Index: 844418 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1052. Min Act: -0.1700

Data Index: 966712 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1210. Min Act: -0.1700

Data Index: 1105423 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.2155. Min Range: -3.2155

Max Act: 3.1368. Min Act: -0.1700

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 650