Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 938 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3860. Min Act: -0.1700

Data Index: 760800 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3621. Min Act: -0.1700

Data Index: 729470 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3558. Min Act: -0.1700

Data Index: 1147423 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3081. Min Act: -0.1700

Data Index: 870605 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3274. Min Act: -0.1700

Data Index: 452399 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.3002. Min Act: -0.1700

Data Index: 1238836 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.2566. Min Act: -0.1700

Data Index: 624011 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.2252. Min Act: -0.1700

Data Index: 332057 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.2183. Min Act: -0.1700

Data Index: 683502 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1912. Min Act: -0.1700

Data Index: 800588 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1942. Min Act: -0.1700

Data Index: 96699 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1725. Min Act: -0.1700

Data Index: 1078932 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1197457 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1823. Min Act: -0.1700

Data Index: 190962 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1626. Min Act: -0.1700

Data Index: 360312 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1736. Min Act: -0.1700

Data Index: 92790 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1393. Min Act: -0.1700

Data Index: 831143 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1650. Min Act: -0.1700

Data Index: 1031077 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1329. Min Act: -0.1700

Data Index: 316274 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.3860. Min Range: -3.3860

Max Act: 3.1266. Min Act: -0.1700

Data Index: 1092956 (C4 (Web Text))

Max Activating Token Index: 575