Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 607 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.4073. Min Act: -0.1700

Data Index: 650127 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.3445. Min Act: -0.1700

Data Index: 1059400 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.3131. Min Act: -0.1700

Data Index: 360513 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2974. Min Act: -0.1700

Data Index: 387946 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2817. Min Act: -0.1700

Data Index: 288086 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2817. Min Act: -0.1700

Data Index: 1155507 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2660. Min Act: -0.1700

Data Index: 1069460 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1300880 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2817. Min Act: -0.1700

Data Index: 521892 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2189. Min Act: -0.1700

Data Index: 468945 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1067600 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2346. Min Act: -0.1700

Data Index: 490640 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 185894 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 245351 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2189. Min Act: -0.1700

Data Index: 839321 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2346. Min Act: -0.1700

Data Index: 942998 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2189. Min Act: -0.1700

Data Index: 950622 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2346. Min Act: -0.1700

Data Index: 952627 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1053029 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 3.4073. Min Range: -3.4073

Max Act: 3.2503. Min Act: -0.1700

Data Index: 369409 (C4 (Web Text))

Max Activating Token Index: 4