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

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

Neuron 1922 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: 3.7509. Min Range: -3.7509

Max Act: 3.7509. Min Act: -0.1700

Data Index: 377997 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6985. Min Act: -0.1700

Data Index: 63618 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6412. Min Act: -0.1700

Data Index: 1109000 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6737. Min Act: -0.1697

Data Index: 492875 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6410. Min Act: -0.1696

Data Index: 160445 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6045. Min Act: -0.1700

Data Index: 245424 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.6030. Min Act: -0.1700

Data Index: 80072 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5734. Min Act: -0.1700

Data Index: 1207734 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5549. Min Act: -0.1700

Data Index: 1100197 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5593. Min Act: -0.1700

Data Index: 835794 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5453. Min Act: -0.1700

Data Index: 1040147 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1307949 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5373. Min Act: -0.1700

Data Index: 744392 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5303. Min Act: -0.1700

Data Index: 936922 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5310. Min Act: -0.1700

Data Index: 924206 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5290. Min Act: -0.1699

Data Index: 204106 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5204. Min Act: -0.1700

Data Index: 121788 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5206. Min Act: -0.1699

Data Index: 104901 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5212. Min Act: -0.1700

Data Index: 467711 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5085. Min Act: -0.1700

Data Index: 753021 (C4 (Web Text))

Max Activating Token Index: 718