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

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

Neuron 1434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.3436. Min Act: -0.1700

Data Index: 429150 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1077884 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2651. Min Act: -0.1700

Data Index: 190006 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2494. Min Act: -0.1700

Data Index: 138942 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2494. Min Act: -0.1700

Data Index: 509329 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2337. Min Act: -0.1700

Data Index: 316291 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2337. Min Act: -0.1700

Data Index: 1342282 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2179. Min Act: -0.1700

Data Index: 522589 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2179. Min Act: -0.1700

Data Index: 676330 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2179. Min Act: -0.1700

Data Index: 63576 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2179. Min Act: -0.1700

Data Index: 666511 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2022. Min Act: -0.1700

Data Index: 856773 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2179. Min Act: -0.1700

Data Index: 693392 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.1865. Min Act: -0.1700

Data Index: 1292036 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2022. Min Act: -0.1700

Data Index: 509884 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.1865. Min Act: -0.1700

Data Index: 1113745 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.1707. Min Act: -0.1700

Data Index: 645616 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.1865. Min Act: -0.1700

Data Index: 648771 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.2022. Min Act: -0.1700

Data Index: 974169 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.3436. Min Range: -3.3436

Max Act: 3.1707. Min Act: -0.1700

Data Index: 915810 (C4 (Web Text))

Max Activating Token Index: 144