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

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

Neuron 278 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: 3.4615. Min Range: -3.4615

Max Act: 3.4615. Min Act: -0.1700

Data Index: 833467 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.1788. Min Act: -0.1700

Data Index: 1165476 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.1473. Min Act: -0.1700

Data Index: 660086 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.1316. Min Act: -0.1700

Data Index: 361331 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.1158. Min Act: -0.1700

Data Index: 984380 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0843. Min Act: -0.1700

Data Index: 814726 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0685. Min Act: -0.1700

Data Index: 714810 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0211. Min Act: -0.1700

Data Index: 239838 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0211. Min Act: -0.1700

Data Index: 215884 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0527. Min Act: -0.1700

Data Index: 715662 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0211. Min Act: -0.1700

Data Index: 128367 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0527. Min Act: -0.1700

Data Index: 360435 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0527. Min Act: -0.1700

Data Index: 58257 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0211. Min Act: -0.1700

Data Index: 84939 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0211. Min Act: -0.1700

Data Index: 117214 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.4615. Min Range: -3.4615

Max Act: 3.0053. Min Act: -0.1700

Data Index: 736269 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 3.4615. Min Range: -3.4615

Max Act: 2.9737. Min Act: -0.1700

Data Index: 101235 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.4615. Min Range: -3.4615

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1054859 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 3.4615. Min Range: -3.4615

Max Act: 2.9579. Min Act: -0.1700

Data Index: 593127 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.4615. Min Range: -3.4615

Max Act: 2.9737. Min Act: -0.1700

Data Index: 108734 (C4 (Web Text))

Max Activating Token Index: 165