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

Dataset: Open Web Text

Neuron 2482 in Layer 3

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: 4.0430. Min Range: -4.0430

Max Act: 4.0430. Min Act: -0.1700

Data Index: 4294692 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.9208. Min Act: -0.1700

Data Index: 556670 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8707. Min Act: -0.1700

Data Index: 4107090 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8833. Min Act: -0.1700

Data Index: 3809356 (Open Web Text)

Max Activating Token Index: 389

Text #4

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8518. Min Act: -0.1700

Data Index: 4107088 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8260. Min Act: -0.1700

Data Index: 8620306 (Open Web Text)

Max Activating Token Index: 247

Text #6

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8455. Min Act: -0.1700

Data Index: 221905 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7993. Min Act: -0.1700

Data Index: 710214 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7985. Min Act: -0.1700

Data Index: 3568683 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7929. Min Act: -0.1700

Data Index: 7298815 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.8039. Min Act: -0.1700

Data Index: 6905250 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7962. Min Act: -0.1700

Data Index: 7722825 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7632. Min Act: -0.1700

Data Index: 2525389 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7843. Min Act: -0.1700

Data Index: 8247796 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7744. Min Act: -0.1700

Data Index: 3395997 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7660. Min Act: -0.1700

Data Index: 8651277 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7778. Min Act: -0.1700

Data Index: 2462899 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7482. Min Act: -0.1700

Data Index: 4656877 (Open Web Text)

Max Activating Token Index: 393

Text #18

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7871. Min Act: -0.1700

Data Index: 5723975 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 4.0430. Min Range: -4.0430

Max Act: 3.7326. Min Act: -0.1700

Data Index: 3568684 (Open Web Text)

Max Activating Token Index: 257