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

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

Neuron 647 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: 4.1516. Min Range: -4.1516

Max Act: 4.1516. Min Act: -0.1700

Data Index: 1167055 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.9953. Min Act: -0.1700

Data Index: 340039 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.9328. Min Act: -0.1700

Data Index: 742012 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.9015. Min Act: -0.1700

Data Index: 1248332 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8390. Min Act: -0.1700

Data Index: 455122 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8077. Min Act: -0.1700

Data Index: 1312513 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8702. Min Act: -0.1700

Data Index: 428782 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8702. Min Act: -0.1700

Data Index: 1239713 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8390. Min Act: -0.1700

Data Index: 917949 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.9015. Min Act: -0.1700

Data Index: 1217292 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8077. Min Act: -0.1700

Data Index: 1208223 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7764. Min Act: -0.1700

Data Index: 836189 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8390. Min Act: -0.1700

Data Index: 420426 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7764. Min Act: -0.1700

Data Index: 397774 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7764. Min Act: -0.1700

Data Index: 596032 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.8077. Min Act: -0.1700

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7451. Min Act: -0.1700

Data Index: 944896 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7138. Min Act: -0.1700

Data Index: 117749 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7451. Min Act: -0.1700

Data Index: 809560 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 4.1516. Min Range: -4.1516

Max Act: 3.7138. Min Act: -0.1699

Data Index: 1261232 (C4 (Web Text))

Max Activating Token Index: 438