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

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

Neuron 1162 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: 4.9774. Min Range: -4.9774

Max Act: 4.9774. Min Act: -0.1700

Data Index: 1137893 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8415. Min Act: -0.1699

Data Index: 1005403 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.7701. Min Act: -0.1684

Data Index: 1090185 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.7341. Min Act: -0.1699

Data Index: 766902 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.7389. Min Act: -0.1686

Data Index: 1183584 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.7083. Min Act: -0.1699

Data Index: 1173668 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.6612. Min Act: -0.1695

Data Index: 158598 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.6424. Min Act: -0.1597

Data Index: 986025 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.6421. Min Act: -0.1519

Data Index: 624214 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.6684. Min Act: -0.1700

Data Index: 334886 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.6343. Min Act: -0.1700

Data Index: 1213090 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5299. Min Act: -0.1696

Data Index: 1380938 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5385. Min Act: -0.1699

Data Index: 65034 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5298. Min Act: -0.1696

Data Index: 1065975 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5432. Min Act: -0.1688

Data Index: 495798 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5126. Min Act: -0.1700

Data Index: 319472 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.5055. Min Act: -0.1686

Data Index: 1439665 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.4733. Min Act: -0.1700

Data Index: 1248911 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.4583. Min Act: -0.1699

Data Index: 532923 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.4257. Min Act: -0.1700

Data Index: 1047498 (C4 (Web Text))

Max Activating Token Index: 324