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

Dataset: Open Web Text

Neuron 2667 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: 5.0809. Min Range: -5.0809

Max Act: 5.0809. Min Act: -0.1700

Data Index: 2960265 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.9745. Min Act: -0.1700

Data Index: 1009550 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.8752. Min Act: -0.1700

Data Index: 5167973 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.8147. Min Act: -0.1700

Data Index: 1729626 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.8136. Min Act: -0.1700

Data Index: 2518518 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.8350. Min Act: -0.1700

Data Index: 6987847 (Open Web Text)

Max Activating Token Index: 726

Text #6

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7906. Min Act: -0.1700

Data Index: 4458799 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7787. Min Act: -0.1700

Data Index: 5245378 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7874. Min Act: -0.1700

Data Index: 7923726 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.8087. Min Act: -0.1700

Data Index: 2147780 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7501. Min Act: -0.1700

Data Index: 1823649 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7724. Min Act: -0.1697

Data Index: 3053126 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7261. Min Act: -0.1700

Data Index: 5876459 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7527. Min Act: -0.1700

Data Index: 3741216 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7730. Min Act: -0.1700

Data Index: 4258328 (Open Web Text)

Max Activating Token Index: 869

Text #15

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7483. Min Act: -0.1700

Data Index: 2694569 (Open Web Text)

Max Activating Token Index: 801

Text #16

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7483. Min Act: -0.1700

Data Index: 2324164 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7274. Min Act: -0.1699

Data Index: 3360307 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7082. Min Act: -0.1700

Data Index: 7485694 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 5.0809. Min Range: -5.0809

Max Act: 4.7429. Min Act: -0.1700

Data Index: 7592999 (Open Web Text)

Max Activating Token Index: 687