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

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

Neuron 1243 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: 5.3580. Min Range: -5.3580

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1298431 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.2955. Min Act: -0.1700

Data Index: 290798 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.2955. Min Act: -0.1700

Data Index: 73757 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.2330. Min Act: -0.1700

Data Index: 245976 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.2017. Min Act: -0.1700

Data Index: 525642 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1392. Min Act: -0.1700

Data Index: 1202642 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1080. Min Act: -0.1700

Data Index: 796218 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1392. Min Act: -0.1700

Data Index: 424819 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1392. Min Act: -0.1700

Data Index: 1136671 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1705. Min Act: -0.1700

Data Index: 1067698 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1392. Min Act: -0.1700

Data Index: 743241 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0767. Min Act: -0.1700

Data Index: 199347 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0767. Min Act: -0.1700

Data Index: 1223531 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1080. Min Act: -0.1700

Data Index: 890144 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1080. Min Act: -0.1700

Data Index: 1190756 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0455. Min Act: -0.1700

Data Index: 531038 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0455. Min Act: -0.1700

Data Index: 483044 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0455. Min Act: -0.1700

Data Index: 461400 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.1080. Min Act: -0.1700

Data Index: 392872 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 5.3580. Min Range: -5.3580

Max Act: 5.0767. Min Act: -0.1700

Data Index: 111504 (C4 (Web Text))

Max Activating Token Index: 570