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

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

Neuron 264 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.4153. Min Act: -0.1700

Data Index: 450192 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3839. Min Act: -0.1700

Data Index: 498076 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 1282269 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 374345 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 742623 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 816001 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 440502 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2740. Min Act: -0.1700

Data Index: 869931 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2897. Min Act: -0.1700

Data Index: 1088546 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2897. Min Act: -0.1700

Data Index: 29924 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2740. Min Act: -0.1700

Data Index: 1106203 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 1116732 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 264355 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 839507 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 981095 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 1231926 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 882047 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 918867 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2897. Min Act: -0.1700

Data Index: 696620 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3212. Min Act: -0.1700

Data Index: 634860 (C4 (Web Text))

Max Activating Token Index: 131