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

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

Neuron 438 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: 4.6107. Min Range: -4.6107

Max Act: 4.5961. Min Act: -0.1700

Data Index: 1138393 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.6083. Min Act: -0.1700

Data Index: 21178 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.6107. Min Act: -0.1700

Data Index: 1216635 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5507. Min Act: -0.1700

Data Index: 598493 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5571. Min Act: -0.1700

Data Index: 1009786 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5458. Min Act: -0.1700

Data Index: 907401 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5262. Min Act: -0.1700

Data Index: 322765 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5245. Min Act: -0.1700

Data Index: 662431 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4955. Min Act: -0.1700

Data Index: 696208 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5019. Min Act: -0.1700

Data Index: 537950 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4886. Min Act: -0.1700

Data Index: 989518 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.5132. Min Act: -0.1700

Data Index: 76654 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4781. Min Act: -0.1700

Data Index: 374704 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4612. Min Act: -0.1700

Data Index: 702901 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4900. Min Act: -0.1700

Data Index: 1173354 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4774. Min Act: -0.1700

Data Index: 653422 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4741. Min Act: -0.1700

Data Index: 671333 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4298. Min Act: -0.1700

Data Index: 73961 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4423. Min Act: -0.1700

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 4.6107. Min Range: -4.6107

Max Act: 4.4604. Min Act: -0.1700

Data Index: 104217 (C4 (Web Text))

Max Activating Token Index: 87