Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2014 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.5201. Min Act: -0.1700

Data Index: 494071 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1068146 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4887. Min Act: -0.1700

Data Index: 725019 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.4260. Min Act: -0.1700

Data Index: 716275 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3476. Min Act: -0.1700

Data Index: 527711 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3319. Min Act: -0.1700

Data Index: 783602 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3947. Min Act: -0.1700

Data Index: 683840 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3476. Min Act: -0.1700

Data Index: 572915 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3790. Min Act: -0.1700

Data Index: 793758 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3476. Min Act: -0.1700

Data Index: 27710 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3476. Min Act: -0.1700

Data Index: 1357060 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3162. Min Act: -0.1700

Data Index: 345457 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3162. Min Act: -0.1700

Data Index: 1337560 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3319. Min Act: -0.1700

Data Index: 1013360 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3005. Min Act: -0.1700

Data Index: 869498 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3162. Min Act: -0.1700

Data Index: 57119 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.2691. Min Act: -0.1700

Data Index: 1248462 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.3005. Min Act: -0.1700

Data Index: 1024007 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.2534. Min Act: -0.1700

Data Index: 1261083 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 3.5201. Min Range: -3.5201

Max Act: 3.2534. Min Act: -0.1700

Data Index: 74842 (C4 (Web Text))

Max Activating Token Index: 957