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

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

Neuron 1874 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.5536. Min Act: -0.1700

Data Index: 138253 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.4286. Min Act: -0.1700

Data Index: 948373 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.3661. Min Act: -0.1700

Data Index: 576019 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.3036. Min Act: -0.1700

Data Index: 1327183 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.2411. Min Act: -0.1700

Data Index: 958609 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.2411. Min Act: -0.1700

Data Index: 1016305 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.2411. Min Act: -0.1700

Data Index: 834697 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1786. Min Act: -0.1700

Data Index: 259356 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1786. Min Act: -0.1700

Data Index: 298799 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1161. Min Act: -0.1700

Data Index: 315831 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1786. Min Act: -0.1700

Data Index: 609415 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1161. Min Act: -0.1700

Data Index: 79558 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1161. Min Act: -0.1700

Data Index: 1154487 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1161. Min Act: -0.1700

Data Index: 1280046 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.0536. Min Act: -0.1700

Data Index: 414599 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.0536. Min Act: -0.1700

Data Index: 865023 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.1161. Min Act: -0.1700

Data Index: 770899 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.0536. Min Act: -0.1700

Data Index: 1334024 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 7.5536. Min Range: -7.5536

Max Act: 7.0536. Min Act: -0.1700

Data Index: 302074 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 7.5536. Min Range: -7.5536

Max Act: 6.9911. Min Act: -0.1700

Data Index: 405419 (C4 (Web Text))

Max Activating Token Index: 954