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

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

Neuron 246 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: 5.6871. Min Range: -5.6871

Max Act: 5.6871. Min Act: -0.1700

Data Index: 1261221 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.6871. Min Act: -0.1700

Data Index: 628495 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5934. Min Act: -0.1700

Data Index: 220725 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.6559. Min Act: -0.1700

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5934. Min Act: -0.1700

Data Index: 461495 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5621. Min Act: -0.1700

Data Index: 264491 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.6246. Min Act: -0.1700

Data Index: 1146561 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.6559. Min Act: -0.1700

Data Index: 74927 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5934. Min Act: -0.1700

Data Index: 1234363 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5621. Min Act: -0.1700

Data Index: 594119 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5621. Min Act: -0.1699

Data Index: 956606 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5309. Min Act: -0.1700

Data Index: 516172 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4996. Min Act: -0.1700

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4684. Min Act: -0.1700

Data Index: 211494 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5621. Min Act: -0.1700

Data Index: 1046450 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4996. Min Act: -0.1700

Data Index: 1117211 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4996. Min Act: -0.1700

Data Index: 56585 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.5309. Min Act: -0.1700

Data Index: 122095 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4684. Min Act: -0.1700

Data Index: 1155287 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 5.6871. Min Range: -5.6871

Max Act: 5.4684. Min Act: -0.1700

Data Index: 690958 (C4 (Web Text))

Max Activating Token Index: 170