Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.5570. Min Act: -0.1700

Data Index: 518413 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4632. Min Act: -0.1700

Data Index: 502669 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4320. Min Act: -0.1700

Data Index: 1099831 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4007. Min Act: -0.1700

Data Index: 1304951 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4320. Min Act: -0.1700

Data Index: 1332200 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4320. Min Act: -0.1700

Data Index: 711234 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.4007. Min Act: -0.1700

Data Index: 946019 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.3070. Min Act: -0.1700

Data Index: 1256342 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.3695. Min Act: -0.1700

Data Index: 592670 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.3070. Min Act: -0.1700

Data Index: 838904 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2445. Min Act: -0.1700

Data Index: 455750 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2757. Min Act: -0.1700

Data Index: 422086 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2445. Min Act: -0.1700

Data Index: 640267 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2132. Min Act: -0.1700

Data Index: 881295 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2132. Min Act: -0.1700

Data Index: 1276269 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.2132. Min Act: -0.1700

Data Index: 762658 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.1507. Min Act: -0.1700

Data Index: 118235 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.1507. Min Act: -0.1700

Data Index: 437206 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.1507. Min Act: -0.1700

Data Index: 312815 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 5.5570. Min Range: -5.5570

Max Act: 5.1820. Min Act: -0.1700

Data Index: 37538 (C4 (Web Text))

Max Activating Token Index: 736