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

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

Neuron 541 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.1280. Min Act: -0.1700

Data Index: 860454 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.1280. Min Act: -0.1700

Data Index: 1087852 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1039330 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0965. Min Act: -0.1700

Data Index: 847377 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0807. Min Act: -0.1700

Data Index: 392539 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0965. Min Act: -0.1700

Data Index: 669992 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0807. Min Act: -0.1700

Data Index: 554687 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0807. Min Act: -0.1700

Data Index: 46699 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0965. Min Act: -0.1700

Data Index: 699042 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0492. Min Act: -0.1700

Data Index: 191286 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0492. Min Act: -0.1700

Data Index: 902591 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0807. Min Act: -0.1700

Data Index: 927519 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0334. Min Act: -0.1700

Data Index: 288397 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0807. Min Act: -0.1700

Data Index: 233685 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0649. Min Act: -0.1700

Data Index: 879674 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0492. Min Act: -0.1700

Data Index: 1152406 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0649. Min Act: -0.1700

Data Index: 89273 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0492. Min Act: -0.1700

Data Index: 938167 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0018. Min Act: -0.1700

Data Index: 730682 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 3.1280. Min Range: -3.1280

Max Act: 3.0334. Min Act: -0.1700

Data Index: 690807 (C4 (Web Text))

Max Activating Token Index: 819