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

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

Neuron 667 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: 5.9538. Min Range: -5.9538

Max Act: 5.9538. Min Act: -0.1700

Data Index: 1005140 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.8913. Min Act: -0.1700

Data Index: 773812 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7975. Min Act: -0.1700

Data Index: 945193 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7975. Min Act: -0.1700

Data Index: 638074 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7663. Min Act: -0.1700

Data Index: 687031 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7663. Min Act: -0.1700

Data Index: 577984 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7350. Min Act: -0.1700

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7038. Min Act: -0.1699

Data Index: 713957 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7350. Min Act: -0.1700

Data Index: 606051 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7663. Min Act: -0.1700

Data Index: 726728 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6725. Min Act: -0.1699

Data Index: 560102 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7038. Min Act: -0.1700

Data Index: 699474 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.7038. Min Act: -0.1700

Data Index: 1244160 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6725. Min Act: -0.1700

Data Index: 26189 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6725. Min Act: -0.1700

Data Index: 529206 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.5788. Min Act: -0.1699

Data Index: 247239 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6725. Min Act: -0.1700

Data Index: 1283037 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6100. Min Act: -0.1700

Data Index: 532300 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6725. Min Act: -0.1700

Data Index: 743497 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 5.9538. Min Range: -5.9538

Max Act: 5.6100. Min Act: -0.1700

Data Index: 108467 (C4 (Web Text))

Max Activating Token Index: 353