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

Dataset: Open Web Text

Neuron 1402 in Layer 4

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: 3.5659. Min Range: -3.5659

Max Act: 3.5172. Min Act: -0.1700

Data Index: 5152172 (Open Web Text)

Max Activating Token Index: 824

Text #1

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.5659. Min Act: -0.1700

Data Index: 402248 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.4529. Min Act: -0.1700

Data Index: 6906913 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.4321. Min Act: -0.1700

Data Index: 4885026 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.3681. Min Act: -0.1700

Data Index: 4266628 (Open Web Text)

Max Activating Token Index: 620

Text #5

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.3206. Min Act: -0.1700

Data Index: 1712192 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2831. Min Act: -0.1700

Data Index: 621774 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2653. Min Act: -0.1700

Data Index: 6046138 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1663. Min Act: -0.1700

Data Index: 4333910 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2057. Min Act: -0.1700

Data Index: 2691225 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2303. Min Act: -0.1700

Data Index: 4522334 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1822031 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2008. Min Act: -0.1700

Data Index: 7652236 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1898. Min Act: -0.1700

Data Index: 3040965 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.2094. Min Act: -0.1700

Data Index: 5799996 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1625. Min Act: -0.1700

Data Index: 7174043 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1655607 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1648. Min Act: -0.1700

Data Index: 5522424 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.1709. Min Act: -0.1700

Data Index: 3923878 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.5659. Min Range: -3.5659

Max Act: 3.0957. Min Act: -0.1700

Data Index: 3312341 (Open Web Text)

Max Activating Token Index: 1021