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

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

Neuron 729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4897. Min Act: -0.1700

Data Index: 336541 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.0052. Min Act: -0.1700

Data Index: 588695 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.9114. Min Act: -0.1700

Data Index: 981338 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.9192. Min Act: -0.1700

Data Index: 414235 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.9349. Min Act: -0.1700

Data Index: 491022 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.8958. Min Act: -0.1700

Data Index: 398031 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.8411. Min Act: -0.1700

Data Index: 1065505 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7863. Min Act: -0.1700

Data Index: 603276 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.8332. Min Act: -0.1700

Data Index: 1246835 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7785. Min Act: -0.1700

Data Index: 315562 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7550. Min Act: -0.1700

Data Index: 374883 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7316. Min Act: -0.1700

Data Index: 968984 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7159. Min Act: -0.1700

Data Index: 607881 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.6924. Min Act: -0.1700

Data Index: 366001 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7003. Min Act: -0.1700

Data Index: 1072493 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7159. Min Act: -0.1700

Data Index: 62617 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7081. Min Act: -0.1700

Data Index: 504032 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.7394. Min Act: -0.1700

Data Index: 289972 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.6690. Min Act: -0.1700

Data Index: 512916 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 4.4897. Min Range: -4.4897

Max Act: 3.6846. Min Act: -0.1700

Data Index: 1179950 (C4 (Web Text))

Max Activating Token Index: 815