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

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

Neuron 945 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: 3.9825. Min Range: -3.9825

Max Act: 3.9825. Min Act: -0.1700

Data Index: 590476 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.8262. Min Act: -0.1700

Data Index: 867622 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.8262. Min Act: -0.1700

Data Index: 546966 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7949. Min Act: -0.1700

Data Index: 149024 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7949. Min Act: -0.1700

Data Index: 285555 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7636. Min Act: -0.1700

Data Index: 544232 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7949. Min Act: -0.1700

Data Index: 741394 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.8262. Min Act: -0.1700

Data Index: 915047 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7636. Min Act: -0.1700

Data Index: 403570 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7323. Min Act: -0.1700

Data Index: 539678 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7010. Min Act: -0.1700

Data Index: 410289 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7636. Min Act: -0.1700

Data Index: 987222 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7949. Min Act: -0.1700

Data Index: 1273047 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7323. Min Act: -0.1700

Data Index: 2080 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7010. Min Act: -0.1700

Data Index: 231946 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7323. Min Act: -0.1700

Data Index: 836310 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7010. Min Act: -0.1700

Data Index: 961503 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.6697. Min Act: -0.1700

Data Index: 484251 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7010. Min Act: -0.1700

Data Index: 429249 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.9825. Min Range: -3.9825

Max Act: 3.7010. Min Act: -0.1700

Data Index: 122623 (C4 (Web Text))

Max Activating Token Index: 636