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

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

Neuron 1828 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: 3.4633. Min Range: -3.4633

Max Act: 3.4633. Min Act: -0.1700

Data Index: 606604 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.4476. Min Act: -0.1700

Data Index: 687036 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.4163. Min Act: -0.1700

Data Index: 33931 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3849. Min Act: -0.1700

Data Index: 173374 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1241625 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.4006. Min Act: -0.1700

Data Index: 1104847 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1011876 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 596642 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3692. Min Act: -0.1700

Data Index: 504656 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 860169 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3692. Min Act: -0.1700

Data Index: 864610 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 929692 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 333046 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3378. Min Act: -0.1700

Data Index: 978105 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 1015795 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3378. Min Act: -0.1700

Data Index: 21449 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3378. Min Act: -0.1700

Data Index: 625716 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3378. Min Act: -0.1700

Data Index: 1100991 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3535. Min Act: -0.1700

Data Index: 748897 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.4633. Min Range: -3.4633

Max Act: 3.3378. Min Act: -0.1700

Data Index: 24176 (C4 (Web Text))

Max Activating Token Index: 8