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

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

Neuron 50 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: 5.6647. Min Range: -5.6647

Max Act: 5.6647. Min Act: -0.1699

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.6022. Min Act: -0.1700

Data Index: 687020 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.5397. Min Act: -0.1700

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.6022. Min Act: -0.1700

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.4460. Min Act: -0.1700

Data Index: 684129 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.3522. Min Act: -0.1699

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.3210. Min Act: -0.1700

Data Index: 320113 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.2897. Min Act: -0.1700

Data Index: 371157 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.3522. Min Act: -0.1700

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.2897. Min Act: -0.1700

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.2272. Min Act: -0.1700

Data Index: 1014505 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.1960. Min Act: -0.1700

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.1022. Min Act: -0.1700

Data Index: 709591 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.0710. Min Act: -0.1700

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.6647. Min Range: -5.6647

Max Act: 4.9460. Min Act: -0.1699

Data Index: 476555 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.0085. Min Act: -0.1700

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 5.6647. Min Range: -5.6647

Max Act: 4.9772. Min Act: -0.1700

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 5.6647. Min Range: -5.6647

Max Act: 4.9147. Min Act: -0.1700

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 5.6647. Min Range: -5.6647

Max Act: 5.0710. Min Act: -0.1700

Data Index: 869846 (C4 (Web Text))

Max Activating Token Index: 251