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

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

Neuron 1091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1971. Min Range: -4.1971

Max Act: 4.1971. Min Act: -0.1700

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 4.1971. Min Range: -4.1971

Max Act: 4.0408. Min Act: -0.1700

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 4.1971. Min Range: -4.1971

Max Act: 4.0408. Min Act: -0.1700

Data Index: 790247 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 4.1971. Min Range: -4.1971

Max Act: 4.0096. Min Act: -0.1700

Data Index: 163459 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.9783. Min Act: -0.1700

Data Index: 143550 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.9158. Min Act: -0.1700

Data Index: 274581 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.9783. Min Act: -0.1700

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8845. Min Act: -0.1700

Data Index: 250114 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8845. Min Act: -0.1700

Data Index: 860738 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8532. Min Act: -0.1700

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8219. Min Act: -0.1700

Data Index: 1270112 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8532. Min Act: -0.1700

Data Index: 1109266 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8845. Min Act: -0.1700

Data Index: 827073 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8532. Min Act: -0.1700

Data Index: 456154 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8219. Min Act: -0.1700

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8532. Min Act: -0.1700

Data Index: 1127190 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.7750. Min Act: -0.1700

Data Index: 1007587 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.8219. Min Act: -0.1700

Data Index: 923315 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 4.1971. Min Range: -4.1971

Max Act: 3.9158. Min Act: -0.1700

Data Index: 682097 (C4 (Web Text))

Max Activating Token Index: 666