Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 397 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 6.1455. Min Range: -6.1455

Max Act: 6.1142. Min Act: -0.1700

Data Index: 1232592 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 6.1455. Min Range: -6.1455

Max Act: 6.1455. Min Act: -0.1700

Data Index: 37951 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 6.1455. Min Range: -6.1455

Max Act: 6.0205. Min Act: -0.1700

Data Index: 905632 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 6.1455. Min Range: -6.1455

Max Act: 6.0517. Min Act: -0.1700

Data Index: 681566 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9892. Min Act: -0.1700

Data Index: 975663 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9892. Min Act: -0.1700

Data Index: 235647 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9892. Min Act: -0.1700

Data Index: 933384 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9580. Min Act: -0.1700

Data Index: 79430 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8955. Min Act: -0.1700

Data Index: 78009 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8955. Min Act: -0.1700

Data Index: 441507 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9580. Min Act: -0.1700

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8642. Min Act: -0.1700

Data Index: 353935 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8955. Min Act: -0.1700

Data Index: 1302806 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8017. Min Act: -0.1700

Data Index: 584464 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8330. Min Act: -0.1700

Data Index: 566322 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8642. Min Act: -0.1700

Data Index: 827271 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.8017. Min Act: -0.1700

Data Index: 758202 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.7392. Min Act: -0.1700

Data Index: 730228 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.7705. Min Act: -0.1700

Data Index: 1344629 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.7392. Min Act: -0.1700

Data Index: 486135 (C4 (Web Text))

Max Activating Token Index: 790