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

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

Neuron 1519 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.4740. Min Act: -0.1700

Data Index: 979313 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3956. Min Act: -0.1700

Data Index: 573603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3643. Min Act: -0.1697

Data Index: 1290353 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3643. Min Act: -0.1700

Data Index: 1029683 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3486. Min Act: -0.1700

Data Index: 1250989 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3486. Min Act: -0.1700

Data Index: 208458 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3015. Min Act: -0.1700

Data Index: 415550 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3015. Min Act: -0.1700

Data Index: 547513 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.3015. Min Act: -0.1700

Data Index: 153595 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2858. Min Act: -0.1700

Data Index: 695946 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2858. Min Act: -0.1700

Data Index: 585859 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2701. Min Act: -0.1700

Data Index: 837531 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2701. Min Act: -0.1700

Data Index: 31061 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2701. Min Act: -0.1700

Data Index: 586832 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2543. Min Act: -0.1696

Data Index: 199352 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2543. Min Act: -0.1700

Data Index: 504328 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2386. Min Act: -0.1700

Data Index: 350180 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2229. Min Act: -0.1700

Data Index: 880952 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2229. Min Act: -0.1700

Data Index: 580777 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.2229. Min Act: -0.1700

Data Index: 121871 (C4 (Web Text))

Max Activating Token Index: 916