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

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

Neuron 463 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: 5.3743. Min Range: -5.3743

Max Act: 5.3743. Min Act: -0.1700

Data Index: 1344593 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.2180. Min Act: -0.1700

Data Index: 788805 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.2493. Min Act: -0.1700

Data Index: 596896 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.2180. Min Act: -0.1700

Data Index: 4702 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.1868. Min Act: -0.1700

Data Index: 1028773 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.1243. Min Act: -0.1700

Data Index: 369270 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0930. Min Act: -0.1700

Data Index: 888664 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0618. Min Act: -0.1700

Data Index: 172323 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0305. Min Act: -0.1700

Data Index: 306176 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0930. Min Act: -0.1700

Data Index: 71451 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0305. Min Act: -0.1700

Data Index: 646820 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0618. Min Act: -0.1700

Data Index: 1122915 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0930. Min Act: -0.1700

Data Index: 1144172 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0930. Min Act: -0.1700

Data Index: 72378 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 5.3743. Min Range: -5.3743

Max Act: 4.9680. Min Act: -0.1700

Data Index: 585645 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0305. Min Act: -0.1700

Data Index: 440713 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.3743. Min Range: -5.3743

Max Act: 4.9993. Min Act: -0.1700

Data Index: 127206 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0618. Min Act: -0.1700

Data Index: 127610 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 5.3743. Min Range: -5.3743

Max Act: 5.0305. Min Act: -0.1700

Data Index: 659393 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 5.3743. Min Range: -5.3743

Max Act: 4.9993. Min Act: -0.1700

Data Index: 156545 (C4 (Web Text))

Max Activating Token Index: 630