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

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

Neuron 950 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: 7.3522. Min Range: -7.3522

Max Act: 7.3522. Min Act: -0.1700

Data Index: 1051629 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 7.3522. Min Range: -7.3522

Max Act: 7.1022. Min Act: -0.1700

Data Index: 173849 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 7.3522. Min Range: -7.3522

Max Act: 7.1022. Min Act: -0.1700

Data Index: 790246 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.9147. Min Act: -0.1700

Data Index: 910829 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.8522. Min Act: -0.1700

Data Index: 938007 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.9147. Min Act: -0.1700

Data Index: 1237509 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.8522. Min Act: -0.1700

Data Index: 8619 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.8209. Min Act: -0.1700

Data Index: 628066 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7272. Min Act: -0.1700

Data Index: 182470 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7584. Min Act: -0.1700

Data Index: 290874 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7272. Min Act: -0.1700

Data Index: 1249273 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7897. Min Act: -0.1700

Data Index: 269839 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.6647. Min Act: -0.1700

Data Index: 878436 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7272. Min Act: -0.1700

Data Index: 83938 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.7584. Min Act: -0.1700

Data Index: 1318052 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.6959. Min Act: -0.1700

Data Index: 1000300 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.6022. Min Act: -0.1700

Data Index: 559081 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.5397. Min Act: -0.1700

Data Index: 241875 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.6647. Min Act: -0.1700

Data Index: 331355 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 7.3522. Min Range: -7.3522

Max Act: 6.6334. Min Act: -0.1700

Data Index: 900597 (C4 (Web Text))

Max Activating Token Index: 301