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

Dataset: Open Web Text

Neuron 2999 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: 4.2957. Min Range: -4.2957

Max Act: 4.2954. Min Act: -0.1700

Data Index: 1294101 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2823. Min Act: -0.1700

Data Index: 3427145 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2957. Min Act: -0.1700

Data Index: 2737209 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2755. Min Act: -0.1700

Data Index: 2411184 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2403. Min Act: -0.1700

Data Index: 482521 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2558. Min Act: -0.1700

Data Index: 6342587 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2149. Min Act: -0.1700

Data Index: 2406272 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2136. Min Act: -0.1700

Data Index: 240024 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2350. Min Act: -0.1700

Data Index: 3194676 (Open Web Text)

Max Activating Token Index: 302

Text #9

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2221. Min Act: -0.1700

Data Index: 8058801 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2389. Min Act: -0.1700

Data Index: 1677863 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2103. Min Act: -0.1700

Data Index: 3960254 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2256. Min Act: -0.1700

Data Index: 1096843 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2339. Min Act: -0.1700

Data Index: 1096844 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2372. Min Act: -0.1700

Data Index: 1096845 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2074. Min Act: -0.1700

Data Index: 1250915 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2369. Min Act: -0.1700

Data Index: 5081840 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.1953. Min Act: -0.1700

Data Index: 1685558 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.2074. Min Act: -0.1700

Data Index: 527652 (Open Web Text)

Max Activating Token Index: 348

Text #19

Max Range: 4.2957. Min Range: -4.2957

Max Act: 4.1748. Min Act: -0.1700

Data Index: 3457831 (Open Web Text)

Max Activating Token Index: 75