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

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

Neuron 1773 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: 5.4657. Min Range: -5.4657

Max Act: 5.4657. Min Act: -0.1700

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 5.4657. Min Range: -5.4657

Max Act: 5.3095. Min Act: -0.1700

Data Index: 1277530 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 5.4657. Min Range: -5.4657

Max Act: 5.0595. Min Act: -0.1700

Data Index: 503096 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 5.4657. Min Range: -5.4657

Max Act: 5.0595. Min Act: -0.1700

Data Index: 97933 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9032. Min Act: -0.1700

Data Index: 1000756 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9657. Min Act: -0.1700

Data Index: 924397 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9657. Min Act: -0.1700

Data Index: 145174 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 5.4657. Min Range: -5.4657

Max Act: 5.0282. Min Act: -0.1700

Data Index: 1020322 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9970. Min Act: -0.1700

Data Index: 265826 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9345. Min Act: -0.1700

Data Index: 542931 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9970. Min Act: -0.1700

Data Index: 794518 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9345. Min Act: -0.1700

Data Index: 827308 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9345. Min Act: -0.1700

Data Index: 520726 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9345. Min Act: -0.1700

Data Index: 1227102 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9970. Min Act: -0.1700

Data Index: 369479 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.9032. Min Act: -0.1700

Data Index: 977438 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.8095. Min Act: -0.1700

Data Index: 550918 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.8720. Min Act: -0.1700

Data Index: 352631 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.8720. Min Act: -0.1700

Data Index: 1177401 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 5.4657. Min Range: -5.4657

Max Act: 4.8407. Min Act: -0.1700

Data Index: 74447 (C4 (Web Text))

Max Activating Token Index: 444