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

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

Neuron 1169 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: 6.9359. Min Range: -6.9359

Max Act: 6.9359. Min Act: -0.1700

Data Index: 441011 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7964. Min Act: -0.1700

Data Index: 927877 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7523. Min Act: -0.1700

Data Index: 596367 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7751. Min Act: -0.1699

Data Index: 523831 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7307. Min Act: -0.1700

Data Index: 1300623 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7752. Min Act: -0.1700

Data Index: 346396 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7705. Min Act: -0.1700

Data Index: 653262 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7193. Min Act: -0.1699

Data Index: 98195 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6961. Min Act: -0.1700

Data Index: 1225455 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6178. Min Act: -0.1700

Data Index: 243164 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6525. Min Act: -0.1700

Data Index: 870098 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6487. Min Act: -0.1700

Data Index: 577312 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.5854. Min Act: -0.1700

Data Index: 996726 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6508. Min Act: -0.1700

Data Index: 1250193 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6244. Min Act: -0.1700

Data Index: 87762 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.7153. Min Act: -0.1700

Data Index: 357235 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6560. Min Act: -0.1700

Data Index: 36639 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6789. Min Act: -0.1700

Data Index: 671681 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.6524. Min Act: -0.1700

Data Index: 121490 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 6.9359. Min Range: -6.9359

Max Act: 6.5882. Min Act: -0.1700

Data Index: 852471 (C4 (Web Text))

Max Activating Token Index: 932