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

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

Neuron 240 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.4734. Min Act: -0.1700

Data Index: 773130 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.4263. Min Act: -0.1700

Data Index: 1309862 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.4106. Min Act: -0.1700

Data Index: 1050370 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3950. Min Act: -0.1700

Data Index: 1297017 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3793. Min Act: -0.1700

Data Index: 404008 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3950. Min Act: -0.1700

Data Index: 33685 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3950. Min Act: -0.1700

Data Index: 1142316 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.4106. Min Act: -0.1700

Data Index: 1279423 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3950. Min Act: -0.1700

Data Index: 247725 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3793. Min Act: -0.1700

Data Index: 51627 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3636. Min Act: -0.1700

Data Index: 842782 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3479. Min Act: -0.1700

Data Index: 998187 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3793. Min Act: -0.1700

Data Index: 985017 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3636. Min Act: -0.1700

Data Index: 870182 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3636. Min Act: -0.1700

Data Index: 549600 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3636. Min Act: -0.1700

Data Index: 239925 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3479. Min Act: -0.1700

Data Index: 560036 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3322. Min Act: -0.1700

Data Index: 672232 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3479. Min Act: -0.1700

Data Index: 572623 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 3.4734. Min Range: -3.4734

Max Act: 3.3479. Min Act: -0.1700

Data Index: 1028554 (C4 (Web Text))

Max Activating Token Index: 265