Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.5307. Min Act: -0.1700

Data Index: 6188652 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.5100. Min Act: -0.1700

Data Index: 4884640 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4455. Min Act: -0.1700

Data Index: 4620420 (Open Web Text)

Max Activating Token Index: 419

Text #3

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4295. Min Act: -0.1700

Data Index: 6448404 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4253. Min Act: -0.1700

Data Index: 2444041 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4229. Min Act: -0.1700

Data Index: 5227477 (Open Web Text)

Max Activating Token Index: 1002

Text #6

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4138. Min Act: -0.1700

Data Index: 3589578 (Open Web Text)

Max Activating Token Index: 898

Text #7

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4126. Min Act: -0.1700

Data Index: 5975665 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3996. Min Act: -0.1700

Data Index: 7239716 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4090. Min Act: -0.1700

Data Index: 4389063 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3857. Min Act: -0.1700

Data Index: 5674809 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3806. Min Act: -0.1700

Data Index: 396617 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3988. Min Act: -0.1700

Data Index: 3624783 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3772. Min Act: -0.1700

Data Index: 8454497 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3709. Min Act: -0.1700

Data Index: 3887408 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3752. Min Act: -0.1700

Data Index: 6514756 (Open Web Text)

Max Activating Token Index: 414

Text #16

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3734. Min Act: -0.1700

Data Index: 1799605 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3770. Min Act: -0.1700

Data Index: 3221240 (Open Web Text)

Max Activating Token Index: 259

Text #18

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3429. Min Act: -0.1700

Data Index: 5496381 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1943891 (Open Web Text)

Max Activating Token Index: 206