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

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

Neuron 1980 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.2132. Min Act: -0.1700

Data Index: 346247 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.1660. Min Act: -0.1700

Data Index: 46021 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1336150 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.1187. Min Act: -0.1700

Data Index: 468188 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.1345. Min Act: -0.1700

Data Index: 894683 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.1187. Min Act: -0.1700

Data Index: 121058 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0872. Min Act: -0.1700

Data Index: 82441 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0714. Min Act: -0.1700

Data Index: 869038 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0714. Min Act: -0.1700

Data Index: 530495 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0240. Min Act: -0.1700

Data Index: 965934 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0398. Min Act: -0.1700

Data Index: 834961 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0240. Min Act: -0.1700

Data Index: 1356426 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0240. Min Act: -0.1700

Data Index: 818796 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0398. Min Act: -0.1700

Data Index: 1258237 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 3.2132. Min Range: -3.2132

Max Act: 2.9924. Min Act: -0.1700

Data Index: 1197767 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0082. Min Act: -0.1700

Data Index: 933972 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 3.2132. Min Range: -3.2132

Max Act: 3.0082. Min Act: -0.1700

Data Index: 970517 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 3.2132. Min Range: -3.2132

Max Act: 2.9766. Min Act: -0.1700

Data Index: 81903 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.2132. Min Range: -3.2132

Max Act: 2.9766. Min Act: -0.1700

Data Index: 545586 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 3.2132. Min Range: -3.2132

Max Act: 2.9766. Min Act: -0.1700

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 167