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

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

Neuron 783 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.5324. Min Act: -0.1700

Data Index: 504660 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1321348 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3756. Min Act: -0.1700

Data Index: 1097220 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.4070. Min Act: -0.1700

Data Index: 720146 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3600. Min Act: -0.1700

Data Index: 507226 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2972. Min Act: -0.1700

Data Index: 666090 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3443. Min Act: -0.1700

Data Index: 346642 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3286. Min Act: -0.1700

Data Index: 207498 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3129. Min Act: -0.1700

Data Index: 705100 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.3129. Min Act: -0.1700

Data Index: 752336 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1200611 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2814. Min Act: -0.1700

Data Index: 437174 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2972. Min Act: -0.1700

Data Index: 1224128 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1015063 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2814. Min Act: -0.1700

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2657. Min Act: -0.1700

Data Index: 902539 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2343. Min Act: -0.1700

Data Index: 928379 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2343. Min Act: -0.1700

Data Index: 660544 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2657. Min Act: -0.1700

Data Index: 851112 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 3.5324. Min Range: -3.5324

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1139754 (C4 (Web Text))

Max Activating Token Index: 325