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

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

Neuron 807 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: 3.9977. Min Range: -3.9977

Max Act: 3.9977. Min Act: -0.1700

Data Index: 262170 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.8726. Min Act: -0.1700

Data Index: 371991 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.8101. Min Act: -0.1700

Data Index: 650336 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.9352. Min Act: -0.1700

Data Index: 322150 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7788. Min Act: -0.1700

Data Index: 71700 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.8413. Min Act: -0.1700

Data Index: 266831 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7788. Min Act: -0.1700

Data Index: 340454 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7788. Min Act: -0.1700

Data Index: 503458 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.8101. Min Act: -0.1700

Data Index: 1016653 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7788. Min Act: -0.1699

Data Index: 1345501 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7475. Min Act: -0.1700

Data Index: 1512417 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1285534 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7475. Min Act: -0.1700

Data Index: 35139 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7475. Min Act: -0.1700

Data Index: 1087163 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7475. Min Act: -0.1700

Data Index: 779745 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.7475. Min Act: -0.1700

Data Index: 335417 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.6849. Min Act: -0.1700

Data Index: 442473 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1107657 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.6536. Min Act: -0.1700

Data Index: 315544 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 3.9977. Min Range: -3.9977

Max Act: 3.6223. Min Act: -0.1700

Data Index: 417530 (C4 (Web Text))

Max Activating Token Index: 965