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

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

Neuron 457 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: 7.0898. Min Range: -7.0898

Max Act: 7.0898. Min Act: -0.1700

Data Index: 167732 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 7.0898. Min Range: -7.0898

Max Act: 7.0586. Min Act: -0.1700

Data Index: 564548 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.9648. Min Act: -0.1700

Data Index: 183183 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.9648. Min Act: -0.1700

Data Index: 558790 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.9023. Min Act: -0.1700

Data Index: 327068 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.9336. Min Act: -0.1700

Data Index: 1043201 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.8086. Min Act: -0.1700

Data Index: 99050 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7773. Min Act: -0.1700

Data Index: 790583 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.8398. Min Act: -0.1700

Data Index: 795969 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7461. Min Act: -0.1700

Data Index: 760885 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7148. Min Act: -0.1700

Data Index: 302026 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7148. Min Act: -0.1700

Data Index: 195994 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7773. Min Act: -0.1700

Data Index: 158367 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7461. Min Act: -0.1700

Data Index: 925140 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7148. Min Act: -0.1700

Data Index: 990357 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.7148. Min Act: -0.1700

Data Index: 942368 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.6211. Min Act: -0.1700

Data Index: 232983 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.5898. Min Act: -0.1700

Data Index: 1191507 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.6211. Min Act: -0.1700

Data Index: 12697 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 7.0898. Min Range: -7.0898

Max Act: 6.5898. Min Act: -0.1700

Data Index: 1121277 (C4 (Web Text))

Max Activating Token Index: 381