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

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

Neuron 865 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2910. Min Range: -6.2910

Max Act: 6.2910. Min Act: -0.1700

Data Index: 34114 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.8847. Min Act: -0.1700

Data Index: 386663 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 6.2910. Min Range: -6.2910

Max Act: 6.2285. Min Act: -0.1700

Data Index: 1677 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.9785. Min Act: -0.1700

Data Index: 106179 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 6.2910. Min Range: -6.2910

Max Act: 6.0410. Min Act: -0.1700

Data Index: 596190 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.9472. Min Act: -0.1700

Data Index: 1262788 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.9472. Min Act: -0.1700

Data Index: 11299 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 6.2910. Min Range: -6.2910

Max Act: 6.0722. Min Act: -0.1700

Data Index: 17135 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 6.2910. Min Range: -6.2910

Max Act: 6.0097. Min Act: -0.1700

Data Index: 802502 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.9785. Min Act: -0.1700

Data Index: 945310 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.7597. Min Act: -0.1700

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.8535. Min Act: -0.1700

Data Index: 562210 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.6035. Min Act: -0.1700

Data Index: 872269 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.7910. Min Act: -0.1700

Data Index: 950909 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.6972. Min Act: -0.1700

Data Index: 409270 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.6347. Min Act: -0.1700

Data Index: 842859 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.6660. Min Act: -0.1700

Data Index: 791114 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.5097. Min Act: -0.1700

Data Index: 498149 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.8847. Min Act: -0.1700

Data Index: 1180101 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 6.2910. Min Range: -6.2910

Max Act: 5.5722. Min Act: -0.1700

Data Index: 503198 (C4 (Web Text))

Max Activating Token Index: 232