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

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

Neuron 287 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: 3.8613. Min Range: -3.8613

Max Act: 3.8613. Min Act: -0.1700

Data Index: 67582 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.7361. Min Act: -0.1700

Data Index: 417743 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.7361. Min Act: -0.1700

Data Index: 806931 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.7361. Min Act: -0.1700

Data Index: 983771 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.6422. Min Act: -0.1700

Data Index: 721527 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.6422. Min Act: -0.1700

Data Index: 413359 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1314606 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5796. Min Act: -0.1700

Data Index: 572193 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.6109. Min Act: -0.1700

Data Index: 610186 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5796. Min Act: -0.1700

Data Index: 383367 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5796. Min Act: -0.1700

Data Index: 1076908 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5483. Min Act: -0.1700

Data Index: 458747 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5483. Min Act: -0.1700

Data Index: 55048 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5796. Min Act: -0.1700

Data Index: 173096 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.4856. Min Act: -0.1700

Data Index: 571746 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5170. Min Act: -0.1699

Data Index: 29087 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5170. Min Act: -0.1700

Data Index: 467237 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5170. Min Act: -0.1700

Data Index: 867916 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.5170. Min Act: -0.1700

Data Index: 220620 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.8613. Min Range: -3.8613

Max Act: 3.4856. Min Act: -0.1700

Data Index: 58609 (C4 (Web Text))

Max Activating Token Index: 765