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

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

Neuron 572 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: 3.0977. Min Range: -3.0977

Max Act: 3.0977. Min Act: -0.1700

Data Index: 1447943 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0977. Min Act: -0.1700

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0661. Min Act: -0.1700

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0819. Min Act: -0.1700

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0345. Min Act: -0.1700

Data Index: 629194 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0187. Min Act: -0.1700

Data Index: 1369058 (Python Code)

Max Activating Token Index: 245

Text #6

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1427319 (Python Code)

Max Activating Token Index: 606

Text #7

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0029. Min Act: -0.1699

Data Index: 1542348 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0029. Min Act: -0.1700

Data Index: 1646217 (Python Code)

Max Activating Token Index: 526

Text #9

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0029. Min Act: -0.1700

Data Index: 566030 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1605560 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1442175 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1599047 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 3.0977. Min Range: -3.0977

Max Act: 3.0029. Min Act: -0.1700

Data Index: 672204 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9713. Min Act: -0.1697

Data Index: 1638072 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1699

Data Index: 1513116 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1699

Data Index: 1629864 (Python Code)

Max Activating Token Index: 509

Text #17

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1416582 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9713. Min Act: -0.1700

Data Index: 1465639 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 3.0977. Min Range: -3.0977

Max Act: 2.9713. Min Act: -0.1700

Data Index: 1594469 (Python Code)

Max Activating Token Index: 115