Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1245 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7210. Min Act: -0.1700

Data Index: 219561 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7054. Min Act: -0.1700

Data Index: 937758 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6741. Min Act: -0.1700

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6428. Min Act: -0.1700

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6897. Min Act: -0.1700

Data Index: 1105758 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7210. Min Act: -0.1700

Data Index: 1042215 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6897. Min Act: -0.1700

Data Index: 527712 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1097134 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1020113 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6741. Min Act: -0.1700

Data Index: 345752 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6428. Min Act: -0.1700

Data Index: 1271638 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6584. Min Act: -0.1700

Data Index: 1592681 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6897. Min Act: -0.1700

Data Index: 671952 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6897. Min Act: -0.1700

Data Index: 80009 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6741. Min Act: -0.1700

Data Index: 662560 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6584. Min Act: -0.1700

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6584. Min Act: -0.1700

Data Index: 18966 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6741. Min Act: -0.1700

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6584. Min Act: -0.1700

Data Index: 1223541 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 3.7210. Min Range: -3.7210

Max Act: 3.6741. Min Act: -0.1700

Data Index: 307928 (C4 (Web Text))

Max Activating Token Index: 257