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

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

Neuron 624 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: 3.7561. Min Range: -3.7561

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1345076 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.5674. Min Act: -0.1700

Data Index: 16138 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.5223. Min Act: -0.1700

Data Index: 789201 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.5076. Min Act: -0.1700

Data Index: 266310 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.4781. Min Act: -0.1700

Data Index: 575694 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.4531. Min Act: -0.1700

Data Index: 730333 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.4013. Min Act: -0.1700

Data Index: 1053819 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3917. Min Act: -0.1700

Data Index: 349263 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.4078. Min Act: -0.1700

Data Index: 406527 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3928. Min Act: -0.1700

Data Index: 887407 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3848. Min Act: -0.1700

Data Index: 424281 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3737. Min Act: -0.1700

Data Index: 1112395 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3393. Min Act: -0.1700

Data Index: 333995 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3539. Min Act: -0.1700

Data Index: 44118 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3092. Min Act: -0.1700

Data Index: 1136827 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3140. Min Act: -0.1700

Data Index: 700476 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3219. Min Act: -0.1700

Data Index: 817364 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3223. Min Act: -0.1700

Data Index: 1428281 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3163. Min Act: -0.1700

Data Index: 1089257 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.2862. Min Act: -0.1700

Data Index: 781493 (C4 (Web Text))

Max Activating Token Index: 67