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

Dataset: Open Web Text

Neuron 641 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: 4.7932. Min Range: -4.7932

Max Act: 4.7932. Min Act: -0.1700

Data Index: 8322338 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7800. Min Act: -0.1700

Data Index: 3372311 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7352. Min Act: -0.1700

Data Index: 5250232 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7405. Min Act: -0.1700

Data Index: 575582 (Open Web Text)

Max Activating Token Index: 896

Text #4

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.6926. Min Act: -0.1700

Data Index: 563393 (Open Web Text)

Max Activating Token Index: 395

Text #5

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7070. Min Act: -0.1700

Data Index: 8132023 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7100. Min Act: -0.1700

Data Index: 7688645 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7529. Min Act: -0.1700

Data Index: 7435894 (Open Web Text)

Max Activating Token Index: 954

Text #8

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7436. Min Act: -0.1700

Data Index: 7406753 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7130. Min Act: -0.1700

Data Index: 3600275 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7369. Min Act: -0.1700

Data Index: 6674717 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7482. Min Act: -0.1700

Data Index: 3072715 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7096. Min Act: -0.1700

Data Index: 4812960 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7063. Min Act: -0.1700

Data Index: 683719 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7127. Min Act: -0.1700

Data Index: 4156785 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.7301. Min Act: -0.1700

Data Index: 2038733 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.6890. Min Act: -0.1700

Data Index: 4085233 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.6880. Min Act: -0.1700

Data Index: 1163737 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.6922. Min Act: -0.1700

Data Index: 3773596 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.7932. Min Range: -4.7932

Max Act: 4.6701. Min Act: -0.1700

Data Index: 412192 (Open Web Text)

Max Activating Token Index: 675