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

Dataset: Open Web Text

Neuron 442 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: 5.4373. Min Range: -5.4373

Max Act: 5.4373. Min Act: -0.1700

Data Index: 8101169 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.4276. Min Act: -0.1700

Data Index: 6699673 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.3074. Min Act: -0.1700

Data Index: 7750350 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.3086. Min Act: -0.1700

Data Index: 6511268 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.3014. Min Act: -0.1700

Data Index: 6275703 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.3245. Min Act: -0.1700

Data Index: 5563073 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.3158. Min Act: -0.1700

Data Index: 2262825 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.2095. Min Act: -0.1700

Data Index: 6209455 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.2632. Min Act: -0.1700

Data Index: 594312 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1845. Min Act: -0.1700

Data Index: 8331895 (Open Web Text)

Max Activating Token Index: 336

Text #10

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1843. Min Act: -0.1700

Data Index: 8011242 (Open Web Text)

Max Activating Token Index: 633

Text #11

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1746. Min Act: -0.1700

Data Index: 506142 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.2034. Min Act: -0.1700

Data Index: 950165 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1695. Min Act: -0.1700

Data Index: 1286171 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1878. Min Act: -0.1700

Data Index: 6581746 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.2352. Min Act: -0.1700

Data Index: 2243713 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1979. Min Act: -0.1700

Data Index: 7439883 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1609. Min Act: -0.1700

Data Index: 1480924 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.2202. Min Act: -0.1700

Data Index: 8247024 (Open Web Text)

Max Activating Token Index: 143

Text #19

Max Range: 5.4373. Min Range: -5.4373

Max Act: 5.1165. Min Act: -0.1700

Data Index: 4215468 (Open Web Text)

Max Activating Token Index: 1014