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

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

Neuron 1543 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: 3.6807. Min Range: -3.6807

Max Act: 3.6807. Min Act: -0.1700

Data Index: 132677 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5980. Min Act: -0.1700

Data Index: 1039941 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.6057. Min Act: -0.1700

Data Index: 326275 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5879. Min Act: -0.1700

Data Index: 117654 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5604. Min Act: -0.1700

Data Index: 439263 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5396. Min Act: -0.1700

Data Index: 679968 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5524. Min Act: -0.1700

Data Index: 342965 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5294. Min Act: -0.1700

Data Index: 880358 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5342. Min Act: -0.1700

Data Index: 705488 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5195. Min Act: -0.1700

Data Index: 544822 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4967. Min Act: -0.1700

Data Index: 31635 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5114. Min Act: -0.1700

Data Index: 912386 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1260647 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5005. Min Act: -0.1700

Data Index: 1329072 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4889. Min Act: -0.1700

Data Index: 1567963 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4967. Min Act: -0.1700

Data Index: 513510 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5123. Min Act: -0.1700

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4891. Min Act: -0.1700

Data Index: 261941 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4923. Min Act: -0.1700

Data Index: 847062 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.4789. Min Act: -0.1700

Data Index: 696313 (C4 (Web Text))

Max Activating Token Index: 349