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

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

Neuron 1000 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: 3.6350. Min Range: -3.6350

Max Act: 3.6350. Min Act: -0.1700

Data Index: 167415 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.6208. Min Act: -0.1700

Data Index: 475903 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.5400. Min Act: -0.1700

Data Index: 312174 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4792. Min Act: -0.1700

Data Index: 1200617 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4987. Min Act: -0.1700

Data Index: 139413 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4782. Min Act: -0.1700

Data Index: 570991 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4749. Min Act: -0.1700

Data Index: 548064 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4905. Min Act: -0.1700

Data Index: 981805 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4673. Min Act: -0.1700

Data Index: 585519 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4551. Min Act: -0.1700

Data Index: 746294 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4234. Min Act: -0.1700

Data Index: 903975 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.4184. Min Act: -0.1700

Data Index: 484556 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3604. Min Act: -0.1700

Data Index: 1344111 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3392. Min Act: -0.1700

Data Index: 890526 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1222765 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3427. Min Act: -0.1700

Data Index: 4254 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3381. Min Act: -0.1700

Data Index: 1024724 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3367. Min Act: -0.1700

Data Index: 688776 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3230. Min Act: -0.1700

Data Index: 1030153 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 3.6350. Min Range: -3.6350

Max Act: 3.3209. Min Act: -0.1700

Data Index: 734707 (C4 (Web Text))

Max Activating Token Index: 944