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

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

Neuron 1649 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: 3.6622. Min Range: -3.6622

Max Act: 3.6622. Min Act: -0.1607

Data Index: 419204 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.2711. Min Act: -0.1700

Data Index: 668199 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.2575. Min Act: -0.1674

Data Index: 1321123 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1950. Min Act: -0.1700

Data Index: 777563 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1648. Min Act: -0.1699

Data Index: 1284154 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1601. Min Act: -0.1700

Data Index: 832576 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1368. Min Act: -0.1374

Data Index: 696029 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1120. Min Act: -0.1700

Data Index: 205526 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1148. Min Act: -0.1700

Data Index: 910696 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1234. Min Act: -0.1675

Data Index: 354917 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.1259. Min Act: -0.1697

Data Index: 110459 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0989. Min Act: -0.1675

Data Index: 689434 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0672. Min Act: -0.1700

Data Index: 119248 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0906. Min Act: -0.1700

Data Index: 1244956 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0929. Min Act: -0.1552

Data Index: 30675 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0755. Min Act: -0.1688

Data Index: 1320415 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0806. Min Act: -0.1696

Data Index: 1296008 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0490. Min Act: -0.1700

Data Index: 134111 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0474. Min Act: -0.1700

Data Index: 136181 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.0324. Min Act: -0.1700

Data Index: 19609 (C4 (Web Text))

Max Activating Token Index: 362