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

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

Neuron 255 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8077. Min Act: -0.1700

Data Index: 258423 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8703. Min Act: -0.1700

Data Index: 547040 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8703. Min Act: -0.1700

Data Index: 764834 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8703. Min Act: -0.1700

Data Index: 404714 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8390. Min Act: -0.1700

Data Index: 990248 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8390. Min Act: -0.1700

Data Index: 1252731 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8390. Min Act: -0.1700

Data Index: 225439 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8390. Min Act: -0.1700

Data Index: 151478 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7764. Min Act: -0.1700

Data Index: 359256 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8077. Min Act: -0.1700

Data Index: 491596 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7451. Min Act: -0.1700

Data Index: 1174597 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8077. Min Act: -0.1700

Data Index: 555815 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7451. Min Act: -0.1700

Data Index: 528024 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.8390. Min Act: -0.1700

Data Index: 1248849 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7764. Min Act: -0.1700

Data Index: 350658 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7764. Min Act: -0.1700

Data Index: 777126 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7138. Min Act: -0.1700

Data Index: 567916 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7138. Min Act: -0.1700

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.6826. Min Act: -0.1700

Data Index: 61465 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.8703. Min Range: -3.8703

Max Act: 3.7764. Min Act: -0.1700

Data Index: 178170 (C4 (Web Text))

Max Activating Token Index: 347