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

Dataset: Open Web Text

Neuron 3066 in Layer 2

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: 2.3166. Min Range: -2.3166

Max Act: 2.3166. Min Act: -0.1700

Data Index: 2851329 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2772. Min Act: -0.1700

Data Index: 6033342 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2860. Min Act: -0.1700

Data Index: 3460159 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2430. Min Act: -0.1700

Data Index: 3222585 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2860. Min Act: -0.1700

Data Index: 6478545 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2610. Min Act: -0.1700

Data Index: 3600750 (Open Web Text)

Max Activating Token Index: 877

Text #6

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2493. Min Act: -0.1700

Data Index: 6846863 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2492. Min Act: -0.1700

Data Index: 3752433 (Open Web Text)

Max Activating Token Index: 848

Text #8

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2378. Min Act: -0.1700

Data Index: 1595276 (Open Web Text)

Max Activating Token Index: 804

Text #9

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2248. Min Act: -0.1700

Data Index: 1595274 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2205. Min Act: -0.1700

Data Index: 2654640 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2431. Min Act: -0.1700

Data Index: 4922991 (Open Web Text)

Max Activating Token Index: 804

Text #12

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2373. Min Act: -0.1700

Data Index: 6040501 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2342. Min Act: -0.1700

Data Index: 5693454 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2393. Min Act: -0.1700

Data Index: 6029138 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2172. Min Act: -0.1700

Data Index: 2002592 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2198. Min Act: -0.1700

Data Index: 3789360 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2145. Min Act: -0.1700

Data Index: 1778363 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2184. Min Act: -0.1700

Data Index: 2662226 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.3166. Min Range: -2.3166

Max Act: 2.2162. Min Act: -0.1700

Data Index: 4973331 (Open Web Text)

Max Activating Token Index: 163