Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 110 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.8655. Min Act: -0.1700

Data Index: 583255 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.8347. Min Act: -0.1700

Data Index: 1293229 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.8318. Min Act: -0.1700

Data Index: 523772 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.8144. Min Act: -0.1700

Data Index: 576743 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.8098. Min Act: -0.1700

Data Index: 981287 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7896. Min Act: -0.1700

Data Index: 952338 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7890. Min Act: -0.1700

Data Index: 732361 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7592. Min Act: -0.1700

Data Index: 754400 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7784. Min Act: -0.1700

Data Index: 1102603 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7900. Min Act: -0.1700

Data Index: 483272 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7554. Min Act: -0.1700

Data Index: 719015 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7688. Min Act: -0.1700

Data Index: 922594 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7563. Min Act: -0.1700

Data Index: 945687 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7695. Min Act: -0.1700

Data Index: 1039599 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7591. Min Act: -0.1700

Data Index: 1271703 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7468. Min Act: -0.1700

Data Index: 737635 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7449. Min Act: -0.1700

Data Index: 1038133 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7431. Min Act: -0.1700

Data Index: 452691 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7373. Min Act: -0.1700

Data Index: 540576 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 2.8655. Min Range: -2.8655

Max Act: 2.7236. Min Act: -0.1700

Data Index: 686911 (C4 (Web Text))

Max Activating Token Index: 1018