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

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

Neuron 1971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.4862. Min Act: -0.1700

Data Index: 1358724 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.5019. Min Act: -0.1700

Data Index: 1330563 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.3294. Min Act: -0.1700

Data Index: 1144100 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2823. Min Act: -0.1700

Data Index: 911711 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2823. Min Act: -0.1700

Data Index: 1187705 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2980. Min Act: -0.1700

Data Index: 1171311 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2666. Min Act: -0.1700

Data Index: 1072380 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.3137. Min Act: -0.1700

Data Index: 1088635 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2666. Min Act: -0.1700

Data Index: 1034197 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2509. Min Act: -0.1700

Data Index: 1013463 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2509. Min Act: -0.1700

Data Index: 274600 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2823. Min Act: -0.1700

Data Index: 368359 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2509. Min Act: -0.1700

Data Index: 862338 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2509. Min Act: -0.1700

Data Index: 923654 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2194. Min Act: -0.1700

Data Index: 766094 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2666. Min Act: -0.1700

Data Index: 600985 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2037. Min Act: -0.1700

Data Index: 739084 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2351. Min Act: -0.1700

Data Index: 776909 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2037. Min Act: -0.1700

Data Index: 537240 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.5019. Min Range: -3.5019

Max Act: 3.2037. Min Act: -0.1700

Data Index: 529823 (C4 (Web Text))

Max Activating Token Index: 838