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

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

Neuron 1923 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: 3.9174. Min Range: -3.9174

Max Act: 3.9174. Min Act: -0.1700

Data Index: 992946 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.8861. Min Act: -0.1700

Data Index: 90000 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.8236. Min Act: -0.1700

Data Index: 410344 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.8079. Min Act: -0.1700

Data Index: 507765 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7923. Min Act: -0.1700

Data Index: 263788 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7767. Min Act: -0.1700

Data Index: 932345 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7767. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7610. Min Act: -0.1700

Data Index: 434857 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7767. Min Act: -0.1700

Data Index: 759787 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7454. Min Act: -0.1700

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7454. Min Act: -0.1700

Data Index: 340682 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7767. Min Act: -0.1700

Data Index: 958530 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7297. Min Act: -0.1700

Data Index: 878605 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7297. Min Act: -0.1700

Data Index: 126343 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7141. Min Act: -0.1700

Data Index: 1312241 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7297. Min Act: -0.1700

Data Index: 556984 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7141. Min Act: -0.1700

Data Index: 102659 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7141. Min Act: -0.1700

Data Index: 956840 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6828. Min Act: -0.1700

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6984. Min Act: -0.1700

Data Index: 334985 (C4 (Web Text))

Max Activating Token Index: 125