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

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

Neuron 1942 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6514. Min Act: -0.1700

Data Index: 1316459 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6201. Min Act: -0.1700

Data Index: 947351 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5888. Min Act: -0.1700

Data Index: 940832 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5575. Min Act: -0.1700

Data Index: 460966 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5261. Min Act: -0.1700

Data Index: 573564 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5261. Min Act: -0.1700

Data Index: 501501 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 399697 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1022308 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4948. Min Act: -0.1700

Data Index: 348492 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1061555 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1179056 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 559976 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 888072 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4321. Min Act: -0.1700

Data Index: 1097737 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4635. Min Act: -0.1700

Data Index: 902360 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4321. Min Act: -0.1700

Data Index: 507910 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4321. Min Act: -0.1700

Data Index: 950933 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.3851. Min Act: -0.1700

Data Index: 522983 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4321. Min Act: -0.1700

Data Index: 693089 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.4007. Min Act: -0.1700

Data Index: 406618 (C4 (Web Text))

Max Activating Token Index: 684