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

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

Neuron 128 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: 3.1486. Min Range: -3.1486

Max Act: 3.1486. Min Act: -0.1684

Data Index: 272218 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.1107. Min Act: -0.1700

Data Index: 1091549 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0752. Min Act: -0.1700

Data Index: 1121800 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0482. Min Act: -0.1700

Data Index: 3037 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0359. Min Act: -0.1700

Data Index: 609117 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1205991 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0231. Min Act: -0.1700

Data Index: 171021 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0122. Min Act: -0.1700

Data Index: 190426 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.1486. Min Range: -3.1486

Max Act: 3.0060. Min Act: -0.1700

Data Index: 428205 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9922. Min Act: -0.1700

Data Index: 120918 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9807. Min Act: -0.1696

Data Index: 906333 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9857. Min Act: -0.1699

Data Index: 139679 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9807. Min Act: -0.1700

Data Index: 1086552 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9565. Min Act: -0.1700

Data Index: 1003232 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9634. Min Act: -0.1699

Data Index: 844610 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9480. Min Act: -0.1700

Data Index: 411770 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9696. Min Act: -0.1699

Data Index: 649531 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9498. Min Act: -0.1700

Data Index: 1237642 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9429. Min Act: -0.1700

Data Index: 1119631 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9502. Min Act: -0.1700

Data Index: 725052 (C4 (Web Text))

Max Activating Token Index: 78