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

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

Neuron 405 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.9897. Min Act: -0.1700

Data Index: 1008247 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.9584. Min Act: -0.1700

Data Index: 515810 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 984240 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8959. Min Act: -0.1700

Data Index: 1287479 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.9271. Min Act: -0.1700

Data Index: 732766 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 707095 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 682897 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8333. Min Act: -0.1700

Data Index: 1357349 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 578518 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8333. Min Act: -0.1700

Data Index: 990078 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 1076308 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.7395. Min Act: -0.1700

Data Index: 581824 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.7707. Min Act: -0.1700

Data Index: 673483 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8020. Min Act: -0.1700

Data Index: 256139 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.7707. Min Act: -0.1700

Data Index: 1254105 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.7707. Min Act: -0.1700

Data Index: 1114580 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8020. Min Act: -0.1700

Data Index: 728716 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8646. Min Act: -0.1700

Data Index: 647063 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.7395. Min Act: -0.1700

Data Index: 518195 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 3.9897. Min Range: -3.9897

Max Act: 3.8020. Min Act: -0.1700

Data Index: 196529 (C4 (Web Text))

Max Activating Token Index: 17