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

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

Neuron 1506 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: 3.5627. Min Range: -3.5627

Max Act: 3.5627. Min Act: -0.1700

Data Index: 642244 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4687. Min Act: -0.1700

Data Index: 694939 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4060. Min Act: -0.1700

Data Index: 623545 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4060. Min Act: -0.1700

Data Index: 782305 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4060. Min Act: -0.1700

Data Index: 1200997 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.4060. Min Act: -0.1700

Data Index: 530400 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3747. Min Act: -0.1700

Data Index: 1049421 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3433. Min Act: -0.1700

Data Index: 587021 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3433. Min Act: -0.1700

Data Index: 85213 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2805. Min Act: -0.1700

Data Index: 699222 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.3433. Min Act: -0.1700

Data Index: 863987 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2805. Min Act: -0.1700

Data Index: 44115 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2176. Min Act: -0.1700

Data Index: 828169 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2490. Min Act: -0.1700

Data Index: 366205 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2176. Min Act: -0.1700

Data Index: 654419 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2490. Min Act: -0.1700

Data Index: 991320 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2490. Min Act: -0.1700

Data Index: 647371 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2176. Min Act: -0.1700

Data Index: 663755 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2490. Min Act: -0.1700

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.2805. Min Act: -0.1700

Data Index: 107720 (C4 (Web Text))

Max Activating Token Index: 779