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

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

Neuron 1996 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.5987. Min Act: -0.1700

Data Index: 1128260 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4737. Min Act: -0.1700

Data Index: 13789 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.5049. Min Act: -0.1700

Data Index: 1307013 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.5362. Min Act: -0.1700

Data Index: 32393 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4112. Min Act: -0.1700

Data Index: 601168 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4424. Min Act: -0.1700

Data Index: 1062571 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4424. Min Act: -0.1700

Data Index: 1328345 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.5049. Min Act: -0.1700

Data Index: 1188843 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.3799. Min Act: -0.1700

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4424. Min Act: -0.1700

Data Index: 1163849 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4737. Min Act: -0.1700

Data Index: 527339 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4737. Min Act: -0.1700

Data Index: 25847 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4424. Min Act: -0.1700

Data Index: 509076 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4112. Min Act: -0.1700

Data Index: 102197 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4737. Min Act: -0.1700

Data Index: 211425 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4737. Min Act: -0.1700

Data Index: 1051283 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4424. Min Act: -0.1700

Data Index: 477176 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4112. Min Act: -0.1700

Data Index: 1286254 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.4112. Min Act: -0.1700

Data Index: 37728 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 5.5987. Min Range: -5.5987

Max Act: 5.3799. Min Act: -0.1700

Data Index: 1102906 (C4 (Web Text))

Max Activating Token Index: 956