Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 372 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.3185. Min Act: -0.1700

Data Index: 954175 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.3027. Min Act: -0.1700

Data Index: 636939 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2713. Min Act: -0.1700

Data Index: 1137356 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2556. Min Act: -0.1700

Data Index: 726496 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2399. Min Act: -0.1700

Data Index: 727641 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2556. Min Act: -0.1700

Data Index: 491097 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2399. Min Act: -0.1700

Data Index: 1324596 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2399. Min Act: -0.1700

Data Index: 815073 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2242. Min Act: -0.1700

Data Index: 1146643 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1927. Min Act: -0.1700

Data Index: 1152259 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2242. Min Act: -0.1700

Data Index: 947907 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2084. Min Act: -0.1700

Data Index: 791916 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.2084. Min Act: -0.1700

Data Index: 796251 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1770. Min Act: -0.1700

Data Index: 219725 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1612. Min Act: -0.1700

Data Index: 531131 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1612. Min Act: -0.1700

Data Index: 1301330 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1612. Min Act: -0.1700

Data Index: 439996 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1612. Min Act: -0.1700

Data Index: 624642 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1612. Min Act: -0.1700

Data Index: 704397 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.3185. Min Range: -3.3185

Max Act: 3.1455. Min Act: -0.1700

Data Index: 359429 (C4 (Web Text))

Max Activating Token Index: 455