Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1841 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.6286. Min Act: -0.1700

Data Index: 426939 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5817. Min Act: -0.1700

Data Index: 850451 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5660. Min Act: -0.1700

Data Index: 1032962 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5660. Min Act: -0.1700

Data Index: 772952 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5347. Min Act: -0.1700

Data Index: 1162658 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5660. Min Act: -0.1700

Data Index: 690591 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5347. Min Act: -0.1700

Data Index: 585613 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5190. Min Act: -0.1700

Data Index: 1009561 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5033. Min Act: -0.1700

Data Index: 1053392 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5033. Min Act: -0.1700

Data Index: 699249 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4720. Min Act: -0.1700

Data Index: 542941 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4720. Min Act: -0.1700

Data Index: 1114049 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4720. Min Act: -0.1700

Data Index: 683144 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1254330 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4406. Min Act: -0.1700

Data Index: 553471 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4563. Min Act: -0.1700

Data Index: 458699 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4406. Min Act: -0.1700

Data Index: 332723 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4563. Min Act: -0.1700

Data Index: 1193427 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4250. Min Act: -0.1700

Data Index: 82182 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4406. Min Act: -0.1700

Data Index: 821099 (C4 (Web Text))

Max Activating Token Index: 372