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

Dataset: Open Web Text

Neuron 2902 in Layer 1

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: 3.3642. Min Range: -3.3642

Max Act: 3.3642. Min Act: -0.1700

Data Index: 3306754 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2978. Min Act: -0.1700

Data Index: 8798408 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2670. Min Act: -0.1700

Data Index: 6196223 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2546. Min Act: -0.1700

Data Index: 7880547 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2145. Min Act: -0.1700

Data Index: 6571368 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2206. Min Act: -0.1700

Data Index: 1804142 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2233. Min Act: -0.1700

Data Index: 2445660 (Open Web Text)

Max Activating Token Index: 842

Text #7

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1421109 (Open Web Text)

Max Activating Token Index: 192

Text #8

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2338. Min Act: -0.1700

Data Index: 1876605 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2137. Min Act: -0.1700

Data Index: 3854164 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1953. Min Act: -0.1700

Data Index: 3683260 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1990. Min Act: -0.1700

Data Index: 5274137 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.2145. Min Act: -0.1700

Data Index: 6273619 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1947. Min Act: -0.1700

Data Index: 2661957 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1958. Min Act: -0.1700

Data Index: 8782128 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1731. Min Act: -0.1700

Data Index: 1254440 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1694. Min Act: -0.1700

Data Index: 5402213 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1624. Min Act: -0.1700

Data Index: 6835589 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1610. Min Act: -0.1700

Data Index: 4098160 (Open Web Text)

Max Activating Token Index: 119

Text #19

Max Range: 3.3642. Min Range: -3.3642

Max Act: 3.1720. Min Act: -0.1700

Data Index: 2135838 (Open Web Text)

Max Activating Token Index: 431