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

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

Neuron 734 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3853. Min Act: -0.1700

Data Index: 1156225 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3382. Min Act: -0.1700

Data Index: 691950 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3539. Min Act: -0.1700

Data Index: 838627 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2754. Min Act: -0.1700

Data Index: 41168 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2911. Min Act: -0.1700

Data Index: 674200 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1349832 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2911. Min Act: -0.1700

Data Index: 41402 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.3068. Min Act: -0.1700

Data Index: 568166 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2754. Min Act: -0.1700

Data Index: 579507 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2282. Min Act: -0.1700

Data Index: 184628 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1339236 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2597. Min Act: -0.1700

Data Index: 403987 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2597. Min Act: -0.1700

Data Index: 3770 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2440. Min Act: -0.1700

Data Index: 117521 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2597. Min Act: -0.1700

Data Index: 208316 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2440. Min Act: -0.1700

Data Index: 573798 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1140771 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2440. Min Act: -0.1700

Data Index: 699938 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1099823 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.3853. Min Range: -3.3853

Max Act: 3.2597. Min Act: -0.1700

Data Index: 989883 (C4 (Web Text))

Max Activating Token Index: 822