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

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

Neuron 847 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: 5.2426. Min Range: -5.2426

Max Act: 5.2426. Min Act: -0.1700

Data Index: 112534 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 5.2426. Min Range: -5.2426

Max Act: 5.1488. Min Act: -0.1700

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 5.2426. Min Range: -5.2426

Max Act: 5.0238. Min Act: -0.1700

Data Index: 173602 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.9926. Min Act: -0.1700

Data Index: 649746 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.9926. Min Act: -0.1700

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.8676. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.8363. Min Act: -0.1700

Data Index: 769946 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.8676. Min Act: -0.1700

Data Index: 1171492 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.7738. Min Act: -0.1700

Data Index: 329206 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.7113. Min Act: -0.1700

Data Index: 917236 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.6801. Min Act: -0.1700

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.7113. Min Act: -0.1700

Data Index: 467973 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.7113. Min Act: -0.1700

Data Index: 820453 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.6176. Min Act: -0.1700

Data Index: 1090252 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.5863. Min Act: -0.1700

Data Index: 787956 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.4613. Min Act: -0.1700

Data Index: 100387 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.5550. Min Act: -0.1700

Data Index: 840246 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.5550. Min Act: -0.1700

Data Index: 863439 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.4925. Min Act: -0.1700

Data Index: 859332 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 5.2426. Min Range: -5.2426

Max Act: 4.4925. Min Act: -0.1700

Data Index: 653110 (C4 (Web Text))

Max Activating Token Index: 885