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

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

Neuron 1263 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: 5.8543. Min Range: -5.8543

Max Act: 5.8543. Min Act: -0.1700

Data Index: 806492 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.8543. Min Act: -0.1700

Data Index: 1298590 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.8543. Min Act: -0.1700

Data Index: 753148 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.7293. Min Act: -0.1700

Data Index: 1280629 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.6355. Min Act: -0.1700

Data Index: 433837 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4793. Min Act: -0.1700

Data Index: 405142 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4793. Min Act: -0.1700

Data Index: 1031504 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4480. Min Act: -0.1700

Data Index: 447896 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4480. Min Act: -0.1700

Data Index: 1336164 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3543. Min Act: -0.1700

Data Index: 1178243 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4168. Min Act: -0.1700

Data Index: 126690 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3855. Min Act: -0.1700

Data Index: 692083 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3855. Min Act: -0.1700

Data Index: 144225 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4168. Min Act: -0.1700

Data Index: 1102476 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1308782 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3543. Min Act: -0.1700

Data Index: 1057695 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4168. Min Act: -0.1700

Data Index: 698439 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4168. Min Act: -0.1700

Data Index: 939759 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.4168. Min Act: -0.1700

Data Index: 261260 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 5.8543. Min Range: -5.8543

Max Act: 5.3230. Min Act: -0.1700

Data Index: 532529 (C4 (Web Text))

Max Activating Token Index: 763