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

Dataset: Open Web Text

Neuron 2148 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: 3.9411. Min Range: -3.9411

Max Act: 3.9411. Min Act: -0.1700

Data Index: 8410022 (Open Web Text)

Max Activating Token Index: 652

Text #1

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8928. Min Act: -0.1700

Data Index: 1242698 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.9174. Min Act: -0.1700

Data Index: 7767219 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8863. Min Act: -0.1700

Data Index: 6460354 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8547. Min Act: -0.1700

Data Index: 1936377 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8607. Min Act: -0.1700

Data Index: 8115496 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8535. Min Act: -0.1700

Data Index: 5371141 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8233. Min Act: -0.1700

Data Index: 1905766 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8230. Min Act: -0.1700

Data Index: 7577745 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8403. Min Act: -0.1700

Data Index: 3602920 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8086. Min Act: -0.1700

Data Index: 4046442 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8081. Min Act: -0.1700

Data Index: 5552956 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7978. Min Act: -0.1700

Data Index: 909896 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7941. Min Act: -0.1700

Data Index: 3375809 (Open Web Text)

Max Activating Token Index: 122

Text #14

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8054. Min Act: -0.1700

Data Index: 7147845 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7606. Min Act: -0.1700

Data Index: 5852805 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7620. Min Act: -0.1700

Data Index: 7068716 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7932. Min Act: -0.1700

Data Index: 3023210 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7512. Min Act: -0.1700

Data Index: 1928796 (Open Web Text)

Max Activating Token Index: 865

Text #19

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7767. Min Act: -0.1700

Data Index: 3375808 (Open Web Text)

Max Activating Token Index: 723