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

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

Neuron 966 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1639. Min Act: -0.1700

Data Index: 100796 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1324. Min Act: -0.1700

Data Index: 773132 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1324. Min Act: -0.1700

Data Index: 923252 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1009. Min Act: -0.1700

Data Index: 122589 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1003446 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 1182124 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 684349 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1202197 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 58101 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 387428 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 403566 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 335900 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 719580 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 597922 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 378182 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 626746 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0694. Min Act: -0.1700

Data Index: 193167 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 286150 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 31240 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0536. Min Act: -0.1700

Data Index: 384260 (C4 (Web Text))

Max Activating Token Index: 812