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

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

Neuron 1256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.7537. Min Act: -0.1700

Data Index: 269931 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.7224. Min Act: -0.1700

Data Index: 817223 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.7224. Min Act: -0.1700

Data Index: 1323935 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.6911. Min Act: -0.1700

Data Index: 390924 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.6598. Min Act: -0.1700

Data Index: 109361 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5659. Min Act: -0.1700

Data Index: 499780 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.6285. Min Act: -0.1700

Data Index: 542687 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5345. Min Act: -0.1700

Data Index: 123635 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5972. Min Act: -0.1700

Data Index: 641268 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5659. Min Act: -0.1700

Data Index: 1193337 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5345. Min Act: -0.1700

Data Index: 557094 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4719. Min Act: -0.1700

Data Index: 879171 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4719. Min Act: -0.1700

Data Index: 143130 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5345. Min Act: -0.1700

Data Index: 413293 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4719. Min Act: -0.1700

Data Index: 610377 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4719. Min Act: -0.1700

Data Index: 76245 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4405. Min Act: -0.1700

Data Index: 629726 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.5032. Min Act: -0.1700

Data Index: 329905 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4405. Min Act: -0.1700

Data Index: 894088 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 3.7537. Min Range: -3.7537

Max Act: 3.4719. Min Act: -0.1700

Data Index: 1014871 (C4 (Web Text))

Max Activating Token Index: 453