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

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

Neuron 1830 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: 3.1686. Min Range: -3.1686

Max Act: 3.1686. Min Act: -0.1700

Data Index: 726753 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.1112. Min Act: -0.1700

Data Index: 1293181 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0786. Min Act: -0.1700

Data Index: 493669 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0305. Min Act: -0.1700

Data Index: 279011 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0439. Min Act: -0.1700

Data Index: 223163 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0107. Min Act: -0.1700

Data Index: 410504 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0163. Min Act: -0.1700

Data Index: 686761 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.1686. Min Range: -3.1686

Max Act: 3.0103. Min Act: -0.1700

Data Index: 907505 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9927. Min Act: -0.1700

Data Index: 1110675 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9869. Min Act: -0.1700

Data Index: 557259 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9648. Min Act: -0.1700

Data Index: 1118626 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9670. Min Act: -0.1700

Data Index: 560588 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9653. Min Act: -0.1700

Data Index: 421329 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9677. Min Act: -0.1700

Data Index: 1017922 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9573. Min Act: -0.1700

Data Index: 806097 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9477. Min Act: -0.1700

Data Index: 280720 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9615. Min Act: -0.1700

Data Index: 445897 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9675. Min Act: -0.1700

Data Index: 989293 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9561. Min Act: -0.1700

Data Index: 325351 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 3.1686. Min Range: -3.1686

Max Act: 2.9477. Min Act: -0.1700

Data Index: 837167 (C4 (Web Text))

Max Activating Token Index: 641