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

Dataset: Open Web Text

Neuron 1405 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: 4.8230. Min Range: -4.8230

Max Act: 4.8230. Min Act: -0.1700

Data Index: 64924 (Open Web Text)

Max Activating Token Index: 227

Text #1

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.7474. Min Act: -0.1700

Data Index: 8444020 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.7352. Min Act: -0.1700

Data Index: 732208 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.7133. Min Act: -0.1700

Data Index: 2308357 (Open Web Text)

Max Activating Token Index: 91

Text #4

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6871. Min Act: -0.1700

Data Index: 413271 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6880. Min Act: -0.1700

Data Index: 8682086 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6996. Min Act: -0.1700

Data Index: 2079150 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.7054. Min Act: -0.1700

Data Index: 2832445 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6879. Min Act: -0.1700

Data Index: 3676785 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6964. Min Act: -0.1700

Data Index: 891889 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6306. Min Act: -0.1700

Data Index: 5891813 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6551. Min Act: -0.1700

Data Index: 6509914 (Open Web Text)

Max Activating Token Index: 301

Text #12

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6370. Min Act: -0.1700

Data Index: 566472 (Open Web Text)

Max Activating Token Index: 950

Text #13

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6054. Min Act: -0.1700

Data Index: 1330744 (Open Web Text)

Max Activating Token Index: 586

Text #14

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6267. Min Act: -0.1700

Data Index: 7988210 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6486. Min Act: -0.1700

Data Index: 1268919 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6588. Min Act: -0.1700

Data Index: 3650717 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6320. Min Act: -0.1700

Data Index: 1174574 (Open Web Text)

Max Activating Token Index: 982

Text #18

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.6214. Min Act: -0.1700

Data Index: 5727407 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 4.8230. Min Range: -4.8230

Max Act: 4.5827. Min Act: -0.1700

Data Index: 1514776 (Open Web Text)

Max Activating Token Index: 621