Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.8255. Min Act: -0.1700

Data Index: 278978 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7943. Min Act: -0.1700

Data Index: 1022365 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7786. Min Act: -0.1700

Data Index: 455644 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7943. Min Act: -0.1700

Data Index: 479150 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7630. Min Act: -0.1700

Data Index: 493494 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7473. Min Act: -0.1700

Data Index: 1351835 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7473. Min Act: -0.1700

Data Index: 38657 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1082517 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7160. Min Act: -0.1700

Data Index: 1338007 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7004. Min Act: -0.1700

Data Index: 590836 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6691. Min Act: -0.1700

Data Index: 233786 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7160. Min Act: -0.1700

Data Index: 558871 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7004. Min Act: -0.1700

Data Index: 36846 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7004. Min Act: -0.1700

Data Index: 441515 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6847. Min Act: -0.1700

Data Index: 755828 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1318129 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6847. Min Act: -0.1700

Data Index: 776181 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6847. Min Act: -0.1700

Data Index: 1161582 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6691. Min Act: -0.1700

Data Index: 127499 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 3.8255. Min Range: -3.8255

Max Act: 3.6847. Min Act: -0.1700

Data Index: 1272111 (C4 (Web Text))

Max Activating Token Index: 627