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

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

Neuron 1798 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.6749. Min Act: -0.1700

Data Index: 428605 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.4561. Min Act: -0.1700

Data Index: 257682 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.3311. Min Act: -0.1700

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.2999. Min Act: -0.1700

Data Index: 188028 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.2686. Min Act: -0.1700

Data Index: 901840 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.2374. Min Act: -0.1700

Data Index: 749637 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1749. Min Act: -0.1700

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1749. Min Act: -0.1700

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1749. Min Act: -0.1700

Data Index: 231760 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.2061. Min Act: -0.1700

Data Index: 112024 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 174456 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1749. Min Act: -0.1700

Data Index: 901330 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 896671 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 88967 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 962569 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.0811. Min Act: -0.1700

Data Index: 64122 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.1436. Min Act: -0.1700

Data Index: 904396 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 5.6749. Min Range: -5.6749

Max Act: 5.0811. Min Act: -0.1700

Data Index: 787591 (C4 (Web Text))

Max Activating Token Index: 166