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

Dataset: Open Web Text

Neuron 1396 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: 3.3153. Min Range: -3.3153

Max Act: 3.3153. Min Act: -0.1700

Data Index: 6009247 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.3010. Min Act: -0.1700

Data Index: 2127538 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2807. Min Act: -0.1700

Data Index: 2150012 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2572. Min Act: -0.1700

Data Index: 6823077 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2436. Min Act: -0.1700

Data Index: 6840010 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2421. Min Act: -0.1700

Data Index: 1321629 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2301. Min Act: -0.1700

Data Index: 7327213 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1906. Min Act: -0.1700

Data Index: 3967494 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1839. Min Act: -0.1700

Data Index: 2108799 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1794. Min Act: -0.1700

Data Index: 1685023 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1959. Min Act: -0.1700

Data Index: 5216693 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1673. Min Act: -0.1700

Data Index: 4619139 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1083654 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1831. Min Act: -0.1700

Data Index: 8472307 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1271. Min Act: -0.1700

Data Index: 7570887 (Open Web Text)

Max Activating Token Index: 830

Text #15

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1605. Min Act: -0.1700

Data Index: 8413843 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1335935 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1398. Min Act: -0.1700

Data Index: 1773273 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1551. Min Act: -0.1700

Data Index: 4120529 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1222. Min Act: -0.1700

Data Index: 4829515 (Open Web Text)

Max Activating Token Index: 916