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

Dataset: Open Web Text

Neuron 2219 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: 4.3171. Min Range: -4.3171

Max Act: 4.3012. Min Act: -0.1700

Data Index: 3289468 (Open Web Text)

Max Activating Token Index: 47

Text #1

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.3171. Min Act: -0.1700

Data Index: 801231 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.2631. Min Act: -0.1700

Data Index: 640372 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.2091. Min Act: -0.1700

Data Index: 3030826 (Open Web Text)

Max Activating Token Index: 295

Text #4

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.2116. Min Act: -0.1700

Data Index: 1698059 (Open Web Text)

Max Activating Token Index: 65

Text #5

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.2176. Min Act: -0.1700

Data Index: 5364056 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1904. Min Act: -0.1700

Data Index: 5357093 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1679. Min Act: -0.1700

Data Index: 6940642 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1930. Min Act: -0.1700

Data Index: 5395401 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1794. Min Act: -0.1700

Data Index: 7493394 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1604. Min Act: -0.1700

Data Index: 3459525 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1998. Min Act: -0.1700

Data Index: 3431607 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1589. Min Act: -0.1700

Data Index: 1786894 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1888. Min Act: -0.1700

Data Index: 2358196 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1266. Min Act: -0.1700

Data Index: 4785220 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1661. Min Act: -0.1700

Data Index: 942299 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1524. Min Act: -0.1700

Data Index: 5377700 (Open Web Text)

Max Activating Token Index: 223

Text #17

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1430. Min Act: -0.1700

Data Index: 583050 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1490. Min Act: -0.1700

Data Index: 6512349 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 4.3171. Min Range: -4.3171

Max Act: 4.1436. Min Act: -0.1700

Data Index: 1658866 (Open Web Text)

Max Activating Token Index: 338