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

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

Neuron 94 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: 3.4897. Min Range: -3.4897

Max Act: 3.4897. Min Act: -0.1700

Data Index: 357947 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3956. Min Act: -0.1700

Data Index: 471296 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3642. Min Act: -0.1700

Data Index: 1063641 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3014. Min Act: -0.1700

Data Index: 171411 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2543. Min Act: -0.1700

Data Index: 1243400 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2386. Min Act: -0.1700

Data Index: 100879 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2543. Min Act: -0.1700

Data Index: 1306734 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2071. Min Act: -0.1700

Data Index: 195008 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2228. Min Act: -0.1700

Data Index: 923675 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2071. Min Act: -0.1700

Data Index: 139418 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.2228. Min Act: -0.1700

Data Index: 764666 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1914. Min Act: -0.1700

Data Index: 1301964 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1599. Min Act: -0.1700

Data Index: 817883 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1756. Min Act: -0.1700

Data Index: 1174478 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1599. Min Act: -0.1700

Data Index: 24645 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.0969. Min Act: -0.1700

Data Index: 750843 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1441. Min Act: -0.1700

Data Index: 786243 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1756. Min Act: -0.1700

Data Index: 668831 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1599. Min Act: -0.1700

Data Index: 652219 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.1284. Min Act: -0.1700

Data Index: 559447 (C4 (Web Text))

Max Activating Token Index: 566