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

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

Neuron 1668 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: 3.8958. Min Range: -3.8958

Max Act: 3.8958. Min Act: -0.1700

Data Index: 984972 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.8218. Min Act: -0.1664

Data Index: 67090 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.7404. Min Act: -0.1700

Data Index: 532776 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.7185. Min Act: -0.1700

Data Index: 459232 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.7411. Min Act: -0.1700

Data Index: 600927 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.7420. Min Act: -0.1700

Data Index: 889901 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1211179 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6730. Min Act: -0.1699

Data Index: 234019 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.7001. Min Act: -0.1700

Data Index: 1071261 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6617. Min Act: -0.1700

Data Index: 1304408 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6743. Min Act: -0.1700

Data Index: 782171 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6670. Min Act: -0.1700

Data Index: 280188 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6638. Min Act: -0.1700

Data Index: 71352 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1018934 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6099. Min Act: -0.1700

Data Index: 1332456 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6355. Min Act: -0.1700

Data Index: 249884 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6359. Min Act: -0.1700

Data Index: 600108 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.5982. Min Act: -0.1700

Data Index: 304572 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6147. Min Act: -0.1700

Data Index: 730352 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.8958. Min Range: -3.8958

Max Act: 3.6132. Min Act: -0.1700

Data Index: 1107856 (C4 (Web Text))

Max Activating Token Index: 425