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

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

Neuron 508 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.2998. Min Act: -0.1700

Data Index: 224920 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.2685. Min Act: -0.1700

Data Index: 1097794 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.2060. Min Act: -0.1700

Data Index: 524608 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.2060. Min Act: -0.1700

Data Index: 700141 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.1748. Min Act: -0.1700

Data Index: 980486 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.1748. Min Act: -0.1700

Data Index: 1271894 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.1123. Min Act: -0.1700

Data Index: 802729 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.1123. Min Act: -0.1700

Data Index: 156294 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0810. Min Act: -0.1700

Data Index: 1081734 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0810. Min Act: -0.1700

Data Index: 365659 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0810. Min Act: -0.1700

Data Index: 761528 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.1123. Min Act: -0.1700

Data Index: 135283 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0810. Min Act: -0.1700

Data Index: 685284 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0185. Min Act: -0.1700

Data Index: 1063883 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0185. Min Act: -0.1700

Data Index: 347081 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0498. Min Act: -0.1700

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 5.2998. Min Range: -5.2998

Max Act: 5.0185. Min Act: -0.1700

Data Index: 1083901 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.9248. Min Act: -0.1700

Data Index: 1095622 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.9560. Min Act: -0.1700

Data Index: 398381 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 5.2998. Min Range: -5.2998

Max Act: 4.8935. Min Act: -0.1700

Data Index: 483282 (C4 (Web Text))

Max Activating Token Index: 322