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

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

Neuron 1185 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.6071. Min Act: -0.1700

Data Index: 1222610 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5914. Min Act: -0.1700

Data Index: 815196 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5288. Min Act: -0.1700

Data Index: 105821 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5444. Min Act: -0.1700

Data Index: 441679 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4818. Min Act: -0.1700

Data Index: 227837 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5444. Min Act: -0.1700

Data Index: 140099 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5914. Min Act: -0.1700

Data Index: 1292222 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5131. Min Act: -0.1700

Data Index: 546218 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4818. Min Act: -0.1700

Data Index: 610069 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4974. Min Act: -0.1700

Data Index: 946814 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4974. Min Act: -0.1700

Data Index: 759054 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4818. Min Act: -0.1700

Data Index: 471846 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4818. Min Act: -0.1700

Data Index: 85595 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4974. Min Act: -0.1700

Data Index: 526215 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4504. Min Act: -0.1700

Data Index: 973510 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4818. Min Act: -0.1700

Data Index: 914273 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.5288. Min Act: -0.1700

Data Index: 1151586 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4347. Min Act: -0.1700

Data Index: 815337 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1057312 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.4661. Min Act: -0.1700

Data Index: 776202 (C4 (Web Text))

Max Activating Token Index: 534