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

Dataset: Open Web Text

Neuron 2239 in Layer 6

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: 4.4423. Min Range: -4.4423

Max Act: 4.4423. Min Act: -0.1700

Data Index: 818069 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.3406. Min Act: -0.1700

Data Index: 2382457 (Open Web Text)

Max Activating Token Index: 578

Text #2

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.2415. Min Act: -0.1700

Data Index: 408844 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.2507. Min Act: -0.1700

Data Index: 5160717 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1954. Min Act: -0.1700

Data Index: 1326987 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1854. Min Act: -0.1700

Data Index: 8036204 (Open Web Text)

Max Activating Token Index: 431

Text #6

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1787. Min Act: -0.1700

Data Index: 7168320 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1769. Min Act: -0.1700

Data Index: 6637769 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1497. Min Act: -0.1700

Data Index: 4470182 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.2453. Min Act: -0.1700

Data Index: 2234605 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1966. Min Act: -0.1700

Data Index: 5795526 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1953. Min Act: -0.1700

Data Index: 4334170 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1525. Min Act: -0.1700

Data Index: 3818586 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1297. Min Act: -0.1700

Data Index: 5184024 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.1202. Min Act: -0.1700

Data Index: 2279048 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.0720. Min Act: -0.1700

Data Index: 3166091 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.0986. Min Act: -0.1700

Data Index: 2787249 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.0480. Min Act: -0.1700

Data Index: 944278 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.0835. Min Act: -0.1700

Data Index: 3299758 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 4.4423. Min Range: -4.4423

Max Act: 4.0977. Min Act: -0.1700

Data Index: 5742169 (Open Web Text)

Max Activating Token Index: 1010