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

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

Neuron 1014 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: 5.8523. Min Range: -5.8523

Max Act: 5.8523. Min Act: -0.1700

Data Index: 1327828 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6960. Min Act: -0.1699

Data Index: 333 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6960. Min Act: -0.1700

Data Index: 1130608 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6648. Min Act: -0.1700

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6648. Min Act: -0.1700

Data Index: 1269551 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6648. Min Act: -0.1700

Data Index: 427331 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6023. Min Act: -0.1700

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.7273. Min Act: -0.1700

Data Index: 12522 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.6335. Min Act: -0.1700

Data Index: 5165 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5710. Min Act: -0.1700

Data Index: 656750 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5710. Min Act: -0.1700

Data Index: 1205420 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5710. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5710. Min Act: -0.1700

Data Index: 1180138 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5398. Min Act: -0.1700

Data Index: 284799 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5710. Min Act: -0.1700

Data Index: 984057 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.4773. Min Act: -0.1700

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.4773. Min Act: -0.1700

Data Index: 1198870 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5085. Min Act: -0.1700

Data Index: 628157 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5085. Min Act: -0.1700

Data Index: 1068582 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 5.8523. Min Range: -5.8523

Max Act: 5.5085. Min Act: -0.1700

Data Index: 971513 (C4 (Web Text))

Max Activating Token Index: 464