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

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

Neuron 1485 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.9782. Min Act: -0.1700

Data Index: 361098 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.9469. Min Act: -0.1700

Data Index: 816119 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8531. Min Act: -0.1700

Data Index: 1086339 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8218. Min Act: -0.1700

Data Index: 234794 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7280. Min Act: -0.1700

Data Index: 986658 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7280. Min Act: -0.1700

Data Index: 915405 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7593. Min Act: -0.1700

Data Index: 113154 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7593. Min Act: -0.1700

Data Index: 637861 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7280. Min Act: -0.1700

Data Index: 190875 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 1071004 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7280. Min Act: -0.1700

Data Index: 857343 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 1020883 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 1302340 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 968824 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 711298 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6654. Min Act: -0.1700

Data Index: 789548 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 864090 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 228545 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6967. Min Act: -0.1700

Data Index: 62681 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6654. Min Act: -0.1700

Data Index: 917978 (C4 (Web Text))

Max Activating Token Index: 788