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

Dataset: Open Web Text

Neuron 526 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: 4.5427. Min Range: -4.5427

Max Act: 4.5427. Min Act: -0.1700

Data Index: 5511478 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.3765. Min Act: -0.1700

Data Index: 3657734 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.4084. Min Act: -0.1700

Data Index: 3525413 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.3977. Min Act: -0.1700

Data Index: 90267 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.3584. Min Act: -0.1700

Data Index: 1109320 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.3118. Min Act: -0.1700

Data Index: 6698912 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.3043. Min Act: -0.1700

Data Index: 2068520 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.2975. Min Act: -0.1700

Data Index: 4997220 (Open Web Text)

Max Activating Token Index: 236

Text #8

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.2983. Min Act: -0.1700

Data Index: 4719282 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.2107. Min Act: -0.1700

Data Index: 549968 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.2194. Min Act: -0.1700

Data Index: 4329621 (Open Web Text)

Max Activating Token Index: 941

Text #11

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1738. Min Act: -0.1700

Data Index: 6442957 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.2064. Min Act: -0.1700

Data Index: 3740509 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1575. Min Act: -0.1700

Data Index: 656008 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1557. Min Act: -0.1700

Data Index: 7975548 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1657. Min Act: -0.1700

Data Index: 3158195 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1782. Min Act: -0.1700

Data Index: 1609554 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1695. Min Act: -0.1700

Data Index: 7600757 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1233. Min Act: -0.1700

Data Index: 1030034 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 4.5427. Min Range: -4.5427

Max Act: 4.1389. Min Act: -0.1700

Data Index: 4452453 (Open Web Text)

Max Activating Token Index: 167