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

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

Neuron 1913 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0454. Min Range: -5.0454

Max Act: 5.0454. Min Act: -0.1700

Data Index: 27463 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.8892. Min Act: -0.1700

Data Index: 293385 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.7798. Min Act: -0.1700

Data Index: 1277180 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.7642. Min Act: -0.1700

Data Index: 284239 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6860. Min Act: -0.1700

Data Index: 502823 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6235. Min Act: -0.1700

Data Index: 1329200 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6079. Min Act: -0.1700

Data Index: 979412 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6235. Min Act: -0.1700

Data Index: 1186236 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5610. Min Act: -0.1700

Data Index: 454756 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5923. Min Act: -0.1700

Data Index: 1293722 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6392. Min Act: -0.1700

Data Index: 783174 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6079. Min Act: -0.1700

Data Index: 847974 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5610. Min Act: -0.1700

Data Index: 909599 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5610. Min Act: -0.1700

Data Index: 1211164 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5923. Min Act: -0.1700

Data Index: 427907 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5142. Min Act: -0.1700

Data Index: 212548 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5454. Min Act: -0.1700

Data Index: 907703 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5298. Min Act: -0.1700

Data Index: 1195570 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.4517. Min Act: -0.1700

Data Index: 657781 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5298. Min Act: -0.1700

Data Index: 807119 (C4 (Web Text))

Max Activating Token Index: 380