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

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

Neuron 2005 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: 3.8434. Min Range: -3.8434

Max Act: 3.8434. Min Act: -0.1700

Data Index: 598559 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8434. Min Act: -0.1700

Data Index: 27053 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1143225 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8121. Min Act: -0.1700

Data Index: 395164 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8121. Min Act: -0.1700

Data Index: 471386 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8434. Min Act: -0.1700

Data Index: 502277 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7808. Min Act: -0.1700

Data Index: 1204992 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7495. Min Act: -0.1700

Data Index: 877387 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7495. Min Act: -0.1700

Data Index: 1103075 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7808. Min Act: -0.1700

Data Index: 1187845 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8121. Min Act: -0.1700

Data Index: 95492 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7808. Min Act: -0.1700

Data Index: 38301 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7183. Min Act: -0.1700

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7808. Min Act: -0.1700

Data Index: 472863 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1066312 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7183. Min Act: -0.1700

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7495. Min Act: -0.1700

Data Index: 498956 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7808. Min Act: -0.1700

Data Index: 1118549 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7183. Min Act: -0.1700

Data Index: 785361 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 3.8434. Min Range: -3.8434

Max Act: 3.7495. Min Act: -0.1700

Data Index: 797331 (C4 (Web Text))

Max Activating Token Index: 917