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

Dataset: Open Web Text

Neuron 2639 in Layer 0

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: 3.3266. Min Range: -3.3266

Max Act: 3.3266. Min Act: -0.1700

Data Index: 6045573 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2649. Min Act: -0.1700

Data Index: 307878 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2495. Min Act: -0.1700

Data Index: 2896749 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2467. Min Act: -0.1700

Data Index: 1925623 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2243. Min Act: -0.1700

Data Index: 3258144 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1633697 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2219. Min Act: -0.1700

Data Index: 6267448 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2157. Min Act: -0.1700

Data Index: 1075952 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2138. Min Act: -0.1700

Data Index: 3765848 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2139. Min Act: -0.1700

Data Index: 6532329 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2205. Min Act: -0.1700

Data Index: 615981 (Open Web Text)

Max Activating Token Index: 695

Text #11

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2200. Min Act: -0.1700

Data Index: 3382169 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2091. Min Act: -0.1700

Data Index: 1380335 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2034. Min Act: -0.1700

Data Index: 1285674 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2067. Min Act: -0.1700

Data Index: 290986 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1932. Min Act: -0.1700

Data Index: 1844477 (Open Web Text)

Max Activating Token Index: 281

Text #16

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1967. Min Act: -0.1700

Data Index: 2991069 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1877. Min Act: -0.1700

Data Index: 2312830 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1949. Min Act: -0.1700

Data Index: 2307164 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1799. Min Act: -0.1700

Data Index: 1396996 (Open Web Text)

Max Activating Token Index: 13