Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1930 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.5143. Min Act: -0.1700

Data Index: 574266 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.3716. Min Act: -0.1700

Data Index: 1182857 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.3635. Min Act: -0.1700

Data Index: 328306 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.3431. Min Act: -0.1700

Data Index: 713091 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.3287. Min Act: -0.1700

Data Index: 244453 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2631. Min Act: -0.1700

Data Index: 425609 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2647. Min Act: -0.1700

Data Index: 751691 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2417. Min Act: -0.1700

Data Index: 908579 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2380. Min Act: -0.1700

Data Index: 99283 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2266. Min Act: -0.1700

Data Index: 77968 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2315. Min Act: -0.1700

Data Index: 1183686 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2035. Min Act: -0.1700

Data Index: 313495 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2048. Min Act: -0.1700

Data Index: 1176848 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2062. Min Act: -0.1700

Data Index: 309561 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.1934. Min Act: -0.1700

Data Index: 1218614 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.2044. Min Act: -0.1700

Data Index: 162052 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.1987. Min Act: -0.1700

Data Index: 1215242 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.1798. Min Act: -0.1700

Data Index: 923456 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.1948. Min Act: -0.1700

Data Index: 1346425 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.5143. Min Range: -3.5143

Max Act: 3.1887. Min Act: -0.1700

Data Index: 1459446 (Python Code)

Max Activating Token Index: 309