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

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

Neuron 553 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: 3.1153. Min Range: -3.1153

Max Act: 3.1153. Min Act: -0.1700

Data Index: 1101270 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0995. Min Act: -0.1700

Data Index: 788730 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0995. Min Act: -0.1700

Data Index: 94407 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0522. Min Act: -0.1700

Data Index: 963401 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0206. Min Act: -0.1700

Data Index: 89111 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0048. Min Act: -0.1700

Data Index: 222279 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0048. Min Act: -0.1700

Data Index: 607787 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0206. Min Act: -0.1700

Data Index: 675836 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9890. Min Act: -0.1700

Data Index: 403074 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.1153. Min Range: -3.1153

Max Act: 3.0048. Min Act: -0.1700

Data Index: 422632 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 51883 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 519336 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 817646 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 829667 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9573. Min Act: -0.1700

Data Index: 681555 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 1226089 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 1313354 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 517487 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 734751 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 3.1153. Min Range: -3.1153

Max Act: 2.9732. Min Act: -0.1700

Data Index: 261446 (C4 (Web Text))

Max Activating Token Index: 324