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

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

Neuron 351 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: 5.0449. Min Range: -5.0449

Max Act: 5.0449. Min Act: -0.1700

Data Index: 593578 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.9512. Min Act: -0.1700

Data Index: 329980 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.8262. Min Act: -0.1700

Data Index: 931986 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7949. Min Act: -0.1700

Data Index: 499643 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7949. Min Act: -0.1700

Data Index: 790567 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7637. Min Act: -0.1700

Data Index: 680423 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7324. Min Act: -0.1700

Data Index: 207104 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7012. Min Act: -0.1700

Data Index: 280796 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7324. Min Act: -0.1700

Data Index: 1100656 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.6699. Min Act: -0.1700

Data Index: 949262 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7012. Min Act: -0.1700

Data Index: 390587 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.7012. Min Act: -0.1700

Data Index: 23762 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.6387. Min Act: -0.1700

Data Index: 1283203 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.6074. Min Act: -0.1700

Data Index: 1226228 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.5762. Min Act: -0.1700

Data Index: 861603 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.6074. Min Act: -0.1700

Data Index: 782343 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.6074. Min Act: -0.1700

Data Index: 665677 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.5762. Min Act: -0.1700

Data Index: 1150471 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.5449. Min Act: -0.1700

Data Index: 462721 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 5.0449. Min Range: -5.0449

Max Act: 4.5762. Min Act: -0.1700

Data Index: 338952 (C4 (Web Text))

Max Activating Token Index: 535