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

Dataset: Open Web Text

Neuron 1627 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: 5.3897. Min Range: -5.3897

Max Act: 5.3897. Min Act: -0.1700

Data Index: 7105424 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.3481. Min Act: -0.1700

Data Index: 2643882 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.2689. Min Act: -0.1700

Data Index: 8007887 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1846. Min Act: -0.1700

Data Index: 4363454 (Open Web Text)

Max Activating Token Index: 491

Text #4

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1487. Min Act: -0.1700

Data Index: 5301275 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1103. Min Act: -0.1700

Data Index: 5786666 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.0979. Min Act: -0.1700

Data Index: 2067033 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1329. Min Act: -0.1700

Data Index: 2096278 (Open Web Text)

Max Activating Token Index: 715

Text #8

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.0975. Min Act: -0.1700

Data Index: 8644023 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1112. Min Act: -0.1700

Data Index: 8664537 (Open Web Text)

Max Activating Token Index: 519

Text #10

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1085. Min Act: -0.1700

Data Index: 8504269 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1237. Min Act: -0.1700

Data Index: 1907314 (Open Web Text)

Max Activating Token Index: 992

Text #12

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1042. Min Act: -0.1700

Data Index: 6936015 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1250. Min Act: -0.1700

Data Index: 5568364 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1535. Min Act: -0.1700

Data Index: 1446680 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.0951. Min Act: -0.1700

Data Index: 7105419 (Open Web Text)

Max Activating Token Index: 697

Text #16

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1389. Min Act: -0.1700

Data Index: 5124841 (Open Web Text)

Max Activating Token Index: 248

Text #17

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.0727. Min Act: -0.1700

Data Index: 7137935 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1087. Min Act: -0.1700

Data Index: 503422 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 5.3897. Min Range: -5.3897

Max Act: 5.1050. Min Act: -0.1700

Data Index: 1286676 (Open Web Text)

Max Activating Token Index: 356