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

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

Neuron 153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.3472. Min Act: -0.1700

Data Index: 1307870 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.2373. Min Act: -0.1700

Data Index: 1202386 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.2058. Min Act: -0.1700

Data Index: 870229 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.1901. Min Act: -0.1700

Data Index: 1312550 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.1429. Min Act: -0.1700

Data Index: 95197 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.1271. Min Act: -0.1700

Data Index: 219966 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0798. Min Act: -0.1700

Data Index: 514499 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0956. Min Act: -0.1700

Data Index: 718234 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 802038 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0798. Min Act: -0.1700

Data Index: 979983 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 614716 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0798. Min Act: -0.1700

Data Index: 826646 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 952771 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0482. Min Act: -0.1700

Data Index: 1118845 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 961682 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 636125 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 1189337 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0640. Min Act: -0.1700

Data Index: 233902 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0482. Min Act: -0.1700

Data Index: 996524 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.3472. Min Range: -3.3472

Max Act: 3.0482. Min Act: -0.1700

Data Index: 963543 (C4 (Web Text))

Max Activating Token Index: 339