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

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

Neuron 850 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: 3.1233. Min Range: -3.1233

Max Act: 3.1136. Min Act: -0.1700

Data Index: 1002966 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1233. Min Act: -0.1700

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0800. Min Act: -0.1700

Data Index: 316927 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0893. Min Act: -0.1700

Data Index: 635433 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0471. Min Act: -0.1700

Data Index: 507021 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0634. Min Act: -0.1700

Data Index: 833562 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0827. Min Act: -0.1700

Data Index: 1121548 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0276. Min Act: -0.1700

Data Index: 573933 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0522. Min Act: -0.1700

Data Index: 925689 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9795. Min Act: -0.1700

Data Index: 1011727 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0047. Min Act: -0.1700

Data Index: 817078 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9855. Min Act: -0.1700

Data Index: 659058 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9925. Min Act: -0.1700

Data Index: 1095293 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0152. Min Act: -0.1700

Data Index: 283831 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9833. Min Act: -0.1700

Data Index: 515901 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1245922 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9541. Min Act: -0.1700

Data Index: 1313577 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9669. Min Act: -0.1700

Data Index: 451478 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9597. Min Act: -0.1700

Data Index: 700348 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9705. Min Act: -0.1700

Data Index: 666919 (C4 (Web Text))

Max Activating Token Index: 798