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

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

Neuron 94 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.8740. Min Act: -0.1700

Data Index: 449017 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7802. Min Act: -0.1700

Data Index: 303013 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7958. Min Act: -0.1700

Data Index: 995319 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7802. Min Act: -0.1700

Data Index: 359524 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7019. Min Act: -0.1700

Data Index: 1160809 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7176. Min Act: -0.1700

Data Index: 317772 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7176. Min Act: -0.1700

Data Index: 385748 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7019. Min Act: -0.1700

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7019. Min Act: -0.1700

Data Index: 114432 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6863. Min Act: -0.1700

Data Index: 951 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6550. Min Act: -0.1700

Data Index: 1251374 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6550. Min Act: -0.1700

Data Index: 246934 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.7019. Min Act: -0.1700

Data Index: 647174 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6237. Min Act: -0.1700

Data Index: 616261 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6237. Min Act: -0.1700

Data Index: 419966 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6393. Min Act: -0.1700

Data Index: 953988 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6237. Min Act: -0.1700

Data Index: 1217759 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6393. Min Act: -0.1700

Data Index: 338861 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6393. Min Act: -0.1700

Data Index: 555707 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 3.8740. Min Range: -3.8740

Max Act: 3.6706. Min Act: -0.1700

Data Index: 360873 (C4 (Web Text))

Max Activating Token Index: 655