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

Dataset: Open Web Text

Neuron 2294 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: 3.3861. Min Range: -3.3861

Max Act: 3.3861. Min Act: -0.1700

Data Index: 2857108 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.2955. Min Act: -0.1700

Data Index: 3035866 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.2343. Min Act: -0.1700

Data Index: 7819620 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.2403. Min Act: -0.1700

Data Index: 1426526 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.2133. Min Act: -0.1700

Data Index: 4097655 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.2004. Min Act: -0.1700

Data Index: 162616 (Open Web Text)

Max Activating Token Index: 723

Text #6

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1921. Min Act: -0.1700

Data Index: 7676919 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1890. Min Act: -0.1700

Data Index: 6920419 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1542. Min Act: -0.1700

Data Index: 3104396 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1628. Min Act: -0.1700

Data Index: 3165111 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1514. Min Act: -0.1700

Data Index: 1361015 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1417. Min Act: -0.1700

Data Index: 5116196 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1617. Min Act: -0.1700

Data Index: 5176290 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1363. Min Act: -0.1700

Data Index: 8039695 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1373. Min Act: -0.1700

Data Index: 4776342 (Open Web Text)

Max Activating Token Index: 771

Text #15

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1471. Min Act: -0.1700

Data Index: 6627240 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1402. Min Act: -0.1700

Data Index: 7285652 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1374. Min Act: -0.1700

Data Index: 6538356 (Open Web Text)

Max Activating Token Index: 608

Text #18

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1255. Min Act: -0.1700

Data Index: 3766033 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 3.3861. Min Range: -3.3861

Max Act: 3.1145. Min Act: -0.1700

Data Index: 2135861 (Open Web Text)

Max Activating Token Index: 18