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

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

Neuron 123 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: 4.3399. Min Range: -4.3399

Max Act: 4.3399. Min Act: -0.1700

Data Index: 205582 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.3016. Min Act: -0.1700

Data Index: 1090638 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2455. Min Act: -0.1700

Data Index: 557733 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2859. Min Act: -0.1700

Data Index: 544262 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2685. Min Act: -0.1700

Data Index: 750123 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2184. Min Act: -0.1700

Data Index: 1265476 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2861. Min Act: -0.1700

Data Index: 530192 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2181. Min Act: -0.1700

Data Index: 3098 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1988. Min Act: -0.1700

Data Index: 492571 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2545. Min Act: -0.1700

Data Index: 576815 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2618. Min Act: -0.1700

Data Index: 513272 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2181. Min Act: -0.1700

Data Index: 1197205 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1935. Min Act: -0.1700

Data Index: 702600 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.2095. Min Act: -0.1700

Data Index: 38525 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1391. Min Act: -0.1700

Data Index: 579158 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1087. Min Act: -0.1700

Data Index: 149485 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1599. Min Act: -0.1700

Data Index: 1198620 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1073. Min Act: -0.1700

Data Index: 1007149 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.0984. Min Act: -0.1700

Data Index: 223414 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 4.3399. Min Range: -4.3399

Max Act: 4.1251. Min Act: -0.1700

Data Index: 631683 (C4 (Web Text))

Max Activating Token Index: 903