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

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

Neuron 906 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: 3.8437. Min Range: -3.8437

Max Act: 3.8437. Min Act: -0.1700

Data Index: 1306674 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.7186. Min Act: -0.1700

Data Index: 1293723 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6560. Min Act: -0.1700

Data Index: 1059788 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5934. Min Act: -0.1700

Data Index: 950646 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5934. Min Act: -0.1700

Data Index: 1317243 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5934. Min Act: -0.1700

Data Index: 175981 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1116650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1240721 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5307. Min Act: -0.1700

Data Index: 215783 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4837. Min Act: -0.1700

Data Index: 933280 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5307. Min Act: -0.1700

Data Index: 914679 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4524. Min Act: -0.1700

Data Index: 1043848 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4681. Min Act: -0.1700

Data Index: 930313 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4837. Min Act: -0.1700

Data Index: 579577 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4367. Min Act: -0.1700

Data Index: 1069468 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4367. Min Act: -0.1700

Data Index: 1029913 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4524. Min Act: -0.1700

Data Index: 110810 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4524. Min Act: -0.1700

Data Index: 427861 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4054. Min Act: -0.1700

Data Index: 317242 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4367. Min Act: -0.1700

Data Index: 978189 (C4 (Web Text))

Max Activating Token Index: 502