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

Dataset: Open Web Text

Neuron 1287 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: 1.5923. Min Range: -1.5923

Max Act: 1.5871. Min Act: -0.1700

Data Index: 1655903 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5923. Min Act: -0.1700

Data Index: 1137072 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5625. Min Act: -0.1700

Data Index: 7088763 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5498. Min Act: -0.1700

Data Index: 8034496 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5505. Min Act: -0.1700

Data Index: 7516325 (Open Web Text)

Max Activating Token Index: 163

Text #5

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5526. Min Act: -0.1700

Data Index: 5015736 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5526. Min Act: -0.1700

Data Index: 22607 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5300. Min Act: -0.1700

Data Index: 6906178 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5279. Min Act: -0.1700

Data Index: 1842440 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5238. Min Act: -0.1700

Data Index: 646842 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5167. Min Act: -0.1700

Data Index: 8817047 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5194. Min Act: -0.1700

Data Index: 1809031 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5199. Min Act: -0.1700

Data Index: 3714356 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5107. Min Act: -0.1700

Data Index: 4352679 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5109. Min Act: -0.1700

Data Index: 7516324 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5065. Min Act: -0.1700

Data Index: 4934517 (Open Web Text)

Max Activating Token Index: 482

Text #16

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5208. Min Act: -0.1700

Data Index: 4587748 (Open Web Text)

Max Activating Token Index: 342

Text #17

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5188. Min Act: -0.1700

Data Index: 1656801 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5138. Min Act: -0.1700

Data Index: 7016404 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4953. Min Act: -0.1700

Data Index: 2872901 (Open Web Text)

Max Activating Token Index: 257