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

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

Neuron 723 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: 5.1931. Min Range: -5.1931

Max Act: 5.1931. Min Act: -0.1700

Data Index: 312374 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.9118. Min Act: -0.1700

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8493. Min Act: -0.1700

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8181. Min Act: -0.1700

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8181. Min Act: -0.1700

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8493. Min Act: -0.1700

Data Index: 646336 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8181. Min Act: -0.1700

Data Index: 1206078 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8806. Min Act: -0.1700

Data Index: 5165 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.8806. Min Act: -0.1700

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 156832 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7556. Min Act: -0.1700

Data Index: 344568 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.6931. Min Act: -0.1700

Data Index: 402125 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 820793 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7556. Min Act: -0.1700

Data Index: 4604 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7868. Min Act: -0.1700

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 5.1931. Min Range: -5.1931

Max Act: 4.7556. Min Act: -0.1700

Data Index: 30110 (C4 (Web Text))

Max Activating Token Index: 420