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

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

Neuron 1407 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: 3.8480. Min Range: -3.8480

Max Act: 3.8480. Min Act: -0.1700

Data Index: 1187560 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.7925. Min Act: -0.1700

Data Index: 912369 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.7292. Min Act: -0.1700

Data Index: 880101 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6954. Min Act: -0.1700

Data Index: 991685 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6829. Min Act: -0.1700

Data Index: 370440 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.7119. Min Act: -0.1700

Data Index: 148333 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6767. Min Act: -0.1700

Data Index: 360141 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6835. Min Act: -0.1700

Data Index: 882530 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6569. Min Act: -0.1700

Data Index: 802250 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6578. Min Act: -0.1700

Data Index: 65905 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6783. Min Act: -0.1700

Data Index: 1309887 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1193496 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6662. Min Act: -0.1700

Data Index: 734041 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1164509 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6366. Min Act: -0.1700

Data Index: 1239683 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6381. Min Act: -0.1700

Data Index: 651688 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6613. Min Act: -0.1700

Data Index: 1116452 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1321932 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6327. Min Act: -0.1700

Data Index: 918716 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.8480. Min Range: -3.8480

Max Act: 3.6467. Min Act: -0.1700

Data Index: 537905 (C4 (Web Text))

Max Activating Token Index: 622