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

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

Neuron 1360 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: 3.1749. Min Range: -3.1749

Max Act: 3.1749. Min Act: -0.1700

Data Index: 468241 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0172. Min Act: -0.1700

Data Index: 612066 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9855. Min Act: -0.1700

Data Index: 207780 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9697. Min Act: -0.1700

Data Index: 492036 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9222. Min Act: -0.1700

Data Index: 767030 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9064. Min Act: -0.1700

Data Index: 372802 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.9064. Min Act: -0.1700

Data Index: 241329 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8905. Min Act: -0.1700

Data Index: 1231089 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8905. Min Act: -0.1700

Data Index: 79572 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8746. Min Act: -0.1700

Data Index: 370050 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8746. Min Act: -0.1700

Data Index: 1169965 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8905. Min Act: -0.1700

Data Index: 1104853 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8587. Min Act: -0.1700

Data Index: 1151751 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8428. Min Act: -0.1700

Data Index: 480876 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8428. Min Act: -0.1700

Data Index: 4571 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8905. Min Act: -0.1700

Data Index: 1285495 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8587. Min Act: -0.1700

Data Index: 321196 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8587. Min Act: -0.1700

Data Index: 753790 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8428. Min Act: -0.1700

Data Index: 493442 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.1749. Min Range: -3.1749

Max Act: 2.8269. Min Act: -0.1700

Data Index: 1142650 (C4 (Web Text))

Max Activating Token Index: 276