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

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

Neuron 117 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: 8.6743. Min Range: -8.6743

Max Act: 8.6743. Min Act: -0.1700

Data Index: 484176 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.4243. Min Act: -0.1700

Data Index: 300000 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.2993. Min Act: -0.1700

Data Index: 1235480 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.2993. Min Act: -0.1700

Data Index: 21863 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.3618. Min Act: -0.1700

Data Index: 1306390 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.3618. Min Act: -0.1700

Data Index: 583098 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.2368. Min Act: -0.1700

Data Index: 423200 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.1118. Min Act: -0.1700

Data Index: 680178 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.1743. Min Act: -0.1700

Data Index: 404142 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.1743. Min Act: -0.1700

Data Index: 1310202 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.1118. Min Act: -0.1700

Data Index: 239309 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.0181. Min Act: -0.1700

Data Index: 79673 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.0493. Min Act: -0.1700

Data Index: 1219572 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.0181. Min Act: -0.1700

Data Index: 164022 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.0806. Min Act: -0.1700

Data Index: 121538 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 8.6743. Min Range: -8.6743

Max Act: 7.6743. Min Act: -0.1700

Data Index: 1051506 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 8.6743. Min Range: -8.6743

Max Act: 8.0181. Min Act: -0.1700

Data Index: 972936 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 8.6743. Min Range: -8.6743

Max Act: 7.8618. Min Act: -0.1700

Data Index: 456363 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 8.6743. Min Range: -8.6743

Max Act: 7.9556. Min Act: -0.1700

Data Index: 1038520 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 8.6743. Min Range: -8.6743

Max Act: 7.9243. Min Act: -0.1700

Data Index: 246930 (C4 (Web Text))

Max Activating Token Index: 60