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

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

Neuron 1076 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0964. Min Act: -0.1700

Data Index: 627421 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0964. Min Act: -0.1700

Data Index: 1255827 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0648. Min Act: -0.1700

Data Index: 49636 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0648. Min Act: -0.1700

Data Index: 1068997 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0648. Min Act: -0.1700

Data Index: 128152 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0491. Min Act: -0.1700

Data Index: 957784 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0648. Min Act: -0.1700

Data Index: 1333405 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0491. Min Act: -0.1700

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 114918 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0491. Min Act: -0.1700

Data Index: 274746 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 696495 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0491. Min Act: -0.1700

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1038933 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 574022 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 354833 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1246664 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0175. Min Act: -0.1700

Data Index: 1172919 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1005461 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 3.0964. Min Range: -3.0964

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1007000 (C4 (Web Text))

Max Activating Token Index: 151