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

Dataset: Open Web Text

Neuron 697 in Layer 3

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: 3.2536. Min Range: -3.2536

Max Act: 3.2536. Min Act: -0.1700

Data Index: 7421243 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.2251. Min Act: -0.1700

Data Index: 7204972 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.2074. Min Act: -0.1700

Data Index: 6117297 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1307607 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1614. Min Act: -0.1700

Data Index: 5951174 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1572. Min Act: -0.1700

Data Index: 4285374 (Open Web Text)

Max Activating Token Index: 211

Text #6

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1582. Min Act: -0.1700

Data Index: 6167601 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1567. Min Act: -0.1700

Data Index: 2714785 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1213. Min Act: -0.1700

Data Index: 6142816 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1103. Min Act: -0.1700

Data Index: 6089374 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1389. Min Act: -0.1700

Data Index: 5734391 (Open Web Text)

Max Activating Token Index: 508

Text #11

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0898. Min Act: -0.1700

Data Index: 6947054 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1017. Min Act: -0.1700

Data Index: 6104725 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1084. Min Act: -0.1700

Data Index: 647567 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0874. Min Act: -0.1700

Data Index: 8312669 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0753. Min Act: -0.1700

Data Index: 1496712 (Open Web Text)

Max Activating Token Index: 371

Text #16

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0625. Min Act: -0.1700

Data Index: 5569958 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0779. Min Act: -0.1700

Data Index: 126108 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0574. Min Act: -0.1700

Data Index: 7889353 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0798. Min Act: -0.1700

Data Index: 3371766 (Open Web Text)

Max Activating Token Index: 311