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

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

Neuron 1137 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: 3.1469. Min Range: -3.1469

Max Act: 3.1469. Min Act: -0.1700

Data Index: 1188059 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.1469. Min Act: -0.1700

Data Index: 1178650 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0996. Min Act: -0.1700

Data Index: 569196 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0365. Min Act: -0.1700

Data Index: 476854 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0207. Min Act: -0.1700

Data Index: 342768 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.9733. Min Act: -0.1700

Data Index: 1202802 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.9258. Min Act: -0.1700

Data Index: 723377 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.9258. Min Act: -0.1700

Data Index: 648960 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8941. Min Act: -0.1700

Data Index: 1046510 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8623. Min Act: -0.1700

Data Index: 1229853 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8782. Min Act: -0.1700

Data Index: 16971 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8782. Min Act: -0.1700

Data Index: 748286 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8941. Min Act: -0.1700

Data Index: 157310 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8305. Min Act: -0.1700

Data Index: 1191970 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8464. Min Act: -0.1700

Data Index: 221205 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8146. Min Act: -0.1700

Data Index: 1016556 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8623. Min Act: -0.1700

Data Index: 586561 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8464. Min Act: -0.1700

Data Index: 1213454 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.8464. Min Act: -0.1700

Data Index: 973473 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.7509. Min Act: -0.1700

Data Index: 407817 (C4 (Web Text))

Max Activating Token Index: 865