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

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

Neuron 750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.6908. Min Act: -0.1700

Data Index: 416516 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.6283. Min Act: -0.1700

Data Index: 452529 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.4721. Min Act: -0.1700

Data Index: 980137 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.4721. Min Act: -0.1700

Data Index: 1052557 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.4096. Min Act: -0.1700

Data Index: 1248135 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.2533. Min Act: -0.1700

Data Index: 1328345 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.2221. Min Act: -0.1700

Data Index: 42786 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1283. Min Act: -0.1700

Data Index: 1066461 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1596. Min Act: -0.1700

Data Index: 817490 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1908. Min Act: -0.1700

Data Index: 448823 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1596. Min Act: -0.1700

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1283. Min Act: -0.1700

Data Index: 327631 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.0971. Min Act: -0.1700

Data Index: 1222314 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.0971. Min Act: -0.1700

Data Index: 817056 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1596. Min Act: -0.1700

Data Index: 719311 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1596. Min Act: -0.1700

Data Index: 790077 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.0346. Min Act: -0.1700

Data Index: 1085828 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.1283. Min Act: -0.1700

Data Index: 575692 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.0971. Min Act: -0.1700

Data Index: 493538 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 5.6908. Min Range: -5.6908

Max Act: 5.0971. Min Act: -0.1700

Data Index: 466690 (C4 (Web Text))

Max Activating Token Index: 65