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

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

Neuron 281 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: 3.6476. Min Range: -3.6476

Max Act: 3.6476. Min Act: -0.1700

Data Index: 1221180 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.5536. Min Act: -0.1700

Data Index: 1125405 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4910. Min Act: -0.1700

Data Index: 478028 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4596. Min Act: -0.1700

Data Index: 1133838 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4283. Min Act: -0.1700

Data Index: 740291 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4283. Min Act: -0.1700

Data Index: 224787 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.4283. Min Act: -0.1700

Data Index: 444643 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3655. Min Act: -0.1700

Data Index: 628476 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3655. Min Act: -0.1700

Data Index: 352750 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3969. Min Act: -0.1700

Data Index: 200815 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3498. Min Act: -0.1700

Data Index: 1191528 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3498. Min Act: -0.1700

Data Index: 142750 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3184. Min Act: -0.1700

Data Index: 949006 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3498. Min Act: -0.1700

Data Index: 557887 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.2870. Min Act: -0.1700

Data Index: 245095 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3027. Min Act: -0.1700

Data Index: 1301397 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3027. Min Act: -0.1700

Data Index: 811404 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.3027. Min Act: -0.1700

Data Index: 517340 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.2713. Min Act: -0.1700

Data Index: 169410 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 3.6476. Min Range: -3.6476

Max Act: 3.2713. Min Act: -0.1700

Data Index: 11079 (C4 (Web Text))

Max Activating Token Index: 188