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

Dataset: Open Web Text

Neuron 5 in Layer 5

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: 4.4335. Min Range: -4.4335

Max Act: 4.4335. Min Act: -0.1700

Data Index: 4246313 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.3157. Min Act: -0.1700

Data Index: 8246135 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.3402. Min Act: -0.1700

Data Index: 810841 (Open Web Text)

Max Activating Token Index: 710

Text #3

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.2779. Min Act: -0.1700

Data Index: 7612584 (Open Web Text)

Max Activating Token Index: 987

Text #4

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.2260. Min Act: -0.1700

Data Index: 4833940 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1931. Min Act: -0.1700

Data Index: 3198245 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1615. Min Act: -0.1700

Data Index: 4091424 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0824. Min Act: -0.1700

Data Index: 2309646 (Open Web Text)

Max Activating Token Index: 978

Text #8

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1446. Min Act: -0.1700

Data Index: 1610121 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1604. Min Act: -0.1700

Data Index: 2759048 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1313. Min Act: -0.1700

Data Index: 1610122 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1439. Min Act: -0.1700

Data Index: 1844883 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.1365. Min Act: -0.1700

Data Index: 2658330 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0802. Min Act: -0.1700

Data Index: 2156955 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0462. Min Act: -0.1700

Data Index: 6381055 (Open Web Text)

Max Activating Token Index: 880

Text #15

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0759. Min Act: -0.1700

Data Index: 4246314 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0826. Min Act: -0.1700

Data Index: 2149944 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0260. Min Act: -0.1700

Data Index: 3748934 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0458. Min Act: -0.1700

Data Index: 5645729 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 4.4335. Min Range: -4.4335

Max Act: 4.0682. Min Act: -0.1700

Data Index: 3211857 (Open Web Text)

Max Activating Token Index: 745