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

Dataset: Open Web Text

Neuron 2982 in Layer 5

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: 5.3288. Min Range: -5.3288

Max Act: 5.3288. Min Act: -0.1700

Data Index: 2295640 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.2773. Min Act: -0.1700

Data Index: 7602028 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.2446. Min Act: -0.1700

Data Index: 6925449 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.2317. Min Act: -0.1700

Data Index: 4146834 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.2414. Min Act: -0.1700

Data Index: 5830630 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1591. Min Act: -0.1700

Data Index: 757181 (Open Web Text)

Max Activating Token Index: 943

Text #6

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1924. Min Act: -0.1700

Data Index: 5631620 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1798. Min Act: -0.1700

Data Index: 244829 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1807. Min Act: -0.1700

Data Index: 4770798 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1226. Min Act: -0.1700

Data Index: 7844754 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1745. Min Act: -0.1700

Data Index: 3934117 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1626. Min Act: -0.1700

Data Index: 6456483 (Open Web Text)

Max Activating Token Index: 546

Text #12

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1472. Min Act: -0.1700

Data Index: 6530830 (Open Web Text)

Max Activating Token Index: 718

Text #13

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1642. Min Act: -0.1700

Data Index: 6577726 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1181. Min Act: -0.1700

Data Index: 6102049 (Open Web Text)

Max Activating Token Index: 304

Text #15

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1346. Min Act: -0.1700

Data Index: 3580970 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1021. Min Act: -0.1700

Data Index: 3643874 (Open Web Text)

Max Activating Token Index: 941

Text #17

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1177. Min Act: -0.1700

Data Index: 3783529 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1048. Min Act: -0.1700

Data Index: 5191200 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1037. Min Act: -0.1700

Data Index: 5428215 (Open Web Text)

Max Activating Token Index: 750