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

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

Neuron 520 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: 3.4971. Min Range: -3.4971

Max Act: 3.4971. Min Act: -0.1700

Data Index: 6642 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.2932. Min Act: -0.1700

Data Index: 1652236 (Python Code)

Max Activating Token Index: 790

Text #2

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.2460. Min Act: -0.1700

Data Index: 607096 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.2460. Min Act: -0.1700

Data Index: 1493816 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1280436 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1989. Min Act: -0.1700

Data Index: 233483 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1831. Min Act: -0.1700

Data Index: 852038 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1989. Min Act: -0.1700

Data Index: 1224954 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1989. Min Act: -0.1700

Data Index: 1162079 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1831. Min Act: -0.1700

Data Index: 283406 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1516. Min Act: -0.1700

Data Index: 990743 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 907592 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1831. Min Act: -0.1700

Data Index: 505644 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1516. Min Act: -0.1700

Data Index: 1227946 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 234274 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1516. Min Act: -0.1700

Data Index: 221858 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 1178742 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 1309834 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 12358 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.1674. Min Act: -0.1700

Data Index: 519908 (C4 (Web Text))

Max Activating Token Index: 949