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

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

Neuron 382 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: 3.7501. Min Range: -3.7501

Max Act: 3.7501. Min Act: -0.1700

Data Index: 1299497 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.6651. Min Act: -0.1700

Data Index: 478105 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5989. Min Act: -0.1700

Data Index: 10384 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5868. Min Act: -0.1700

Data Index: 273187 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5858. Min Act: -0.1700

Data Index: 799959 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5840. Min Act: -0.1700

Data Index: 841796 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5784. Min Act: -0.1700

Data Index: 274832 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5598. Min Act: -0.1700

Data Index: 813156 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5660. Min Act: -0.1700

Data Index: 280691 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5547. Min Act: -0.1700

Data Index: 550780 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5411. Min Act: -0.1700

Data Index: 321333 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5435. Min Act: -0.1700

Data Index: 378672 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5525. Min Act: -0.1700

Data Index: 541980 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5451. Min Act: -0.1700

Data Index: 1142011 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5366. Min Act: -0.1700

Data Index: 830009 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5268. Min Act: -0.1700

Data Index: 579808 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5136. Min Act: -0.1700

Data Index: 1055687 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5349. Min Act: -0.1700

Data Index: 1261583 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5200. Min Act: -0.1700

Data Index: 842275 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 3.7501. Min Range: -3.7501

Max Act: 3.5315. Min Act: -0.1700

Data Index: 342384 (C4 (Web Text))

Max Activating Token Index: 606