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

Dataset: Open Web Text

Neuron 1506 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: 3.0625. Min Range: -3.0625

Max Act: 3.0625. Min Act: -0.1700

Data Index: 1819179 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8930. Min Act: -0.1700

Data Index: 2165342 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8682. Min Act: -0.1700

Data Index: 7940078 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8474. Min Act: -0.1700

Data Index: 5359512 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8281. Min Act: -0.1700

Data Index: 5349531 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8218. Min Act: -0.1700

Data Index: 4642959 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8067. Min Act: -0.1700

Data Index: 498587 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7786. Min Act: -0.1700

Data Index: 6454111 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.8005. Min Act: -0.1700

Data Index: 3352670 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7773. Min Act: -0.1700

Data Index: 989530 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7593. Min Act: -0.1700

Data Index: 6208496 (Open Web Text)

Max Activating Token Index: 852

Text #11

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7789. Min Act: -0.1700

Data Index: 6476904 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7635. Min Act: -0.1700

Data Index: 8495133 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7810. Min Act: -0.1700

Data Index: 6588866 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7727. Min Act: -0.1700

Data Index: 4958058 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7638. Min Act: -0.1700

Data Index: 1285064 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7669. Min Act: -0.1700

Data Index: 8609699 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7732. Min Act: -0.1700

Data Index: 2534194 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7550. Min Act: -0.1700

Data Index: 4469902 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 3.0625. Min Range: -3.0625

Max Act: 2.7534. Min Act: -0.1700

Data Index: 2096698 (Open Web Text)

Max Activating Token Index: 69