Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1532 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.8431. Min Act: -0.1700

Data Index: 788464 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.7181. Min Act: -0.1700

Data Index: 184228 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.5306. Min Act: -0.1700

Data Index: 1350209 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4681. Min Act: -0.1700

Data Index: 36519 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4368. Min Act: -0.1700

Data Index: 972167 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4368. Min Act: -0.1700

Data Index: 942823 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4368. Min Act: -0.1700

Data Index: 509222 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3743. Min Act: -0.1700

Data Index: 635126 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3743. Min Act: -0.1700

Data Index: 643727 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4056. Min Act: -0.1700

Data Index: 1237908 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4056. Min Act: -0.1700

Data Index: 260787 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4056. Min Act: -0.1700

Data Index: 1200122 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4681. Min Act: -0.1700

Data Index: 138309 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3430. Min Act: -0.1700

Data Index: 1053499 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3430. Min Act: -0.1700

Data Index: 1234651 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3118. Min Act: -0.1700

Data Index: 513567 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.4368. Min Act: -0.1700

Data Index: 316489 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3743. Min Act: -0.1700

Data Index: 417020 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3430. Min Act: -0.1700

Data Index: 431698 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 5.8431. Min Range: -5.8431

Max Act: 5.3430. Min Act: -0.1700

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 129