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

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

Neuron 125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.4293. Min Act: -0.1700

Data Index: 1192378 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.3981. Min Act: -0.1700

Data Index: 345656 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.3356. Min Act: -0.1700

Data Index: 1084218 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2731. Min Act: -0.1700

Data Index: 781465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.3043. Min Act: -0.1700

Data Index: 1139600 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2418. Min Act: -0.1700

Data Index: 769535 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1151880 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1010390 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2106. Min Act: -0.1700

Data Index: 1305477 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2106. Min Act: -0.1700

Data Index: 221661 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2731. Min Act: -0.1700

Data Index: 608850 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1052746 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.1793. Min Act: -0.1700

Data Index: 111012 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2106. Min Act: -0.1700

Data Index: 114737 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2418. Min Act: -0.1700

Data Index: 225184 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.2106. Min Act: -0.1700

Data Index: 817618 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.1793. Min Act: -0.1700

Data Index: 898229 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.1481. Min Act: -0.1700

Data Index: 554689 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.1793. Min Act: -0.1700

Data Index: 426854 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 5.4293. Min Range: -5.4293

Max Act: 5.1481. Min Act: -0.1700

Data Index: 563354 (C4 (Web Text))

Max Activating Token Index: 449