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

Dataset: Open Web Text

Neuron 938 in Layer 4

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: 3.2830. Min Range: -3.2830

Max Act: 3.2830. Min Act: -0.1700

Data Index: 1314712 (Open Web Text)

Max Activating Token Index: 1016

Text #1

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.2190. Min Act: -0.1700

Data Index: 7543452 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.2191. Min Act: -0.1700

Data Index: 5137507 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1576. Min Act: -0.1700

Data Index: 1405795 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1487. Min Act: -0.1700

Data Index: 1388775 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1355. Min Act: -0.1700

Data Index: 6314695 (Open Web Text)

Max Activating Token Index: 821

Text #6

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1493. Min Act: -0.1700

Data Index: 7526510 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1263. Min Act: -0.1700

Data Index: 4527826 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1285. Min Act: -0.1700

Data Index: 2699463 (Open Web Text)

Max Activating Token Index: 692

Text #9

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1053. Min Act: -0.1700

Data Index: 8471232 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1117. Min Act: -0.1700

Data Index: 802550 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1107. Min Act: -0.1700

Data Index: 7940201 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1087. Min Act: -0.1700

Data Index: 601557 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.0851. Min Act: -0.1700

Data Index: 940213 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.0887. Min Act: -0.1700

Data Index: 2887156 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.0709. Min Act: -0.1700

Data Index: 5242331 (Open Web Text)

Max Activating Token Index: 967

Text #16

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.0836. Min Act: -0.1700

Data Index: 7926069 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1107. Min Act: -0.1700

Data Index: 6625966 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.1026. Min Act: -0.1700

Data Index: 4606131 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 3.2830. Min Range: -3.2830

Max Act: 3.0881. Min Act: -0.1700

Data Index: 2418602 (Open Web Text)

Max Activating Token Index: 976