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

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

Neuron 691 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: 3.1330. Min Range: -3.1330

Max Act: 3.1330. Min Act: -0.1700

Data Index: 1045398 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.1330. Min Range: -3.1330

Max Act: 3.0700. Min Act: -0.1700

Data Index: 691305 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.1330. Min Range: -3.1330

Max Act: 3.0542. Min Act: -0.1700

Data Index: 627313 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.1330. Min Range: -3.1330

Max Act: 3.0068. Min Act: -0.1700

Data Index: 32167 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1150994 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1193310 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9752. Min Act: -0.1700

Data Index: 560678 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9118. Min Act: -0.1700

Data Index: 605820 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9594. Min Act: -0.1700

Data Index: 375133 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9435. Min Act: -0.1700

Data Index: 360756 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9435. Min Act: -0.1700

Data Index: 621340 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.9118. Min Act: -0.1700

Data Index: 1059665 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8801. Min Act: -0.1700

Data Index: 13719 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8960. Min Act: -0.1700

Data Index: 899706 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8960. Min Act: -0.1700

Data Index: 682256 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8960. Min Act: -0.1700

Data Index: 1242624 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8801. Min Act: -0.1700

Data Index: 1302225 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8801. Min Act: -0.1700

Data Index: 879156 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8642. Min Act: -0.1700

Data Index: 830367 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.1330. Min Range: -3.1330

Max Act: 2.8642. Min Act: -0.1700

Data Index: 1121222 (C4 (Web Text))

Max Activating Token Index: 898