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

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

Neuron 1864 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.8966. Min Act: -0.1700

Data Index: 1258224 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.8653. Min Act: -0.1700

Data Index: 118297 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.8340. Min Act: -0.1700

Data Index: 660581 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.8184. Min Act: -0.1700

Data Index: 400492 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7401. Min Act: -0.1700

Data Index: 466663 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7871. Min Act: -0.1700

Data Index: 926312 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7871. Min Act: -0.1700

Data Index: 465924 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1309464 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7401. Min Act: -0.1700

Data Index: 1256657 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7245. Min Act: -0.1700

Data Index: 874971 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7089. Min Act: -0.1700

Data Index: 913330 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7245. Min Act: -0.1700

Data Index: 320211 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7089. Min Act: -0.1700

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.6776. Min Act: -0.1700

Data Index: 949521 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7245. Min Act: -0.1700

Data Index: 1065492 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7245. Min Act: -0.1700

Data Index: 771055 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.7089. Min Act: -0.1700

Data Index: 1051981 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.6932. Min Act: -0.1700

Data Index: 1144690 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.6619. Min Act: -0.1700

Data Index: 907245 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.8966. Min Range: -3.8966

Max Act: 3.6776. Min Act: -0.1700

Data Index: 313997 (C4 (Web Text))

Max Activating Token Index: 990