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

Dataset: Open Web Text

Neuron 1378 in Layer 1

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: 1.7149. Min Range: -1.7149

Max Act: 1.7149. Min Act: -0.1696

Data Index: 6871028 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.7045. Min Act: -0.1700

Data Index: 2687849 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.7071. Min Act: -0.1700

Data Index: 8672210 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6833. Min Act: -0.1699

Data Index: 2989159 (Open Web Text)

Max Activating Token Index: 259

Text #4

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6808. Min Act: -0.1683

Data Index: 4454643 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6686. Min Act: -0.1700

Data Index: 2457797 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6690. Min Act: -0.1700

Data Index: 2299048 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6598. Min Act: -0.1698

Data Index: 4262980 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6623. Min Act: -0.1700

Data Index: 3257176 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6567. Min Act: -0.1700

Data Index: 7433423 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6390. Min Act: -0.1700

Data Index: 8201629 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6393. Min Act: -0.1699

Data Index: 7082034 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6440. Min Act: -0.1700

Data Index: 6328660 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6466. Min Act: -0.1700

Data Index: 5709563 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6428. Min Act: -0.1700

Data Index: 5232570 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6467. Min Act: -0.1700

Data Index: 7224996 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6405. Min Act: -0.1699

Data Index: 6472670 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6326. Min Act: -0.1700

Data Index: 8203846 (Open Web Text)

Max Activating Token Index: 288

Text #18

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6423. Min Act: -0.1700

Data Index: 4786344 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6349. Min Act: -0.1689

Data Index: 2793458 (Open Web Text)

Max Activating Token Index: 560