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

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

Neuron 933 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: 5.7605. Min Range: -5.7605

Max Act: 5.6042. Min Act: -0.1700

Data Index: 1176198 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.6667. Min Act: -0.1700

Data Index: 1201835 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.7605. Min Act: -0.1700

Data Index: 70307 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.6667. Min Act: -0.1700

Data Index: 562394 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.7605. Min Act: -0.1700

Data Index: 499887 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.6980. Min Act: -0.1700

Data Index: 920531 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4480. Min Act: -0.1700

Data Index: 959855 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4792. Min Act: -0.1700

Data Index: 670965 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.5105. Min Act: -0.1700

Data Index: 1016339 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.5105. Min Act: -0.1700

Data Index: 276945 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4480. Min Act: -0.1700

Data Index: 849617 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4792. Min Act: -0.1700

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4480. Min Act: -0.1700

Data Index: 374473 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4792. Min Act: -0.1700

Data Index: 605837 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4480. Min Act: -0.1700

Data Index: 232742 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4480. Min Act: -0.1700

Data Index: 412563 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1177732 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4792. Min Act: -0.1700

Data Index: 116791 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4167. Min Act: -0.1700

Data Index: 166010 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 5.7605. Min Range: -5.7605

Max Act: 5.4167. Min Act: -0.1700

Data Index: 796377 (C4 (Web Text))

Max Activating Token Index: 475