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

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

Neuron 124 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5683. Min Act: -0.1700

Data Index: 53139 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5840. Min Act: -0.1700

Data Index: 1343154 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.4743. Min Act: -0.1700

Data Index: 177288 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.4430. Min Act: -0.1700

Data Index: 372999 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3489. Min Act: -0.1700

Data Index: 759395 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.4116. Min Act: -0.1700

Data Index: 829505 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3646. Min Act: -0.1700

Data Index: 69199 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3332. Min Act: -0.1700

Data Index: 387331 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3175. Min Act: -0.1700

Data Index: 373288 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3018. Min Act: -0.1700

Data Index: 321689 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.3175. Min Act: -0.1700

Data Index: 952509 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2704. Min Act: -0.1700

Data Index: 796474 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2546. Min Act: -0.1700

Data Index: 48438 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2546. Min Act: -0.1700

Data Index: 466422 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2704. Min Act: -0.1700

Data Index: 1092466 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2389. Min Act: -0.1700

Data Index: 122326 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2075. Min Act: -0.1700

Data Index: 868366 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2075. Min Act: -0.1700

Data Index: 625273 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2232. Min Act: -0.1700

Data Index: 566609 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.2546. Min Act: -0.1700

Data Index: 40067 (C4 (Web Text))

Max Activating Token Index: 582