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

Dataset: Open Web Text

Neuron 1634 in Layer 5

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: 4.4653. Min Range: -4.4653

Max Act: 4.4653. Min Act: -0.1700

Data Index: 816501 (Open Web Text)

Max Activating Token Index: 684

Text #1

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.3187. Min Act: -0.1700

Data Index: 3767077 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.2279. Min Act: -0.1700

Data Index: 1022491 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.2138. Min Act: -0.1700

Data Index: 3393896 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1577. Min Act: -0.1700

Data Index: 4060597 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1683. Min Act: -0.1700

Data Index: 6675922 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1135. Min Act: -0.1700

Data Index: 7886470 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1258. Min Act: -0.1700

Data Index: 2233934 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1446. Min Act: -0.1700

Data Index: 2767664 (Open Web Text)

Max Activating Token Index: 458

Text #9

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1548. Min Act: -0.1700

Data Index: 4514756 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1716. Min Act: -0.1700

Data Index: 8275779 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1047. Min Act: -0.1700

Data Index: 5795651 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.0958. Min Act: -0.1700

Data Index: 6650674 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1163. Min Act: -0.1700

Data Index: 4751355 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1035. Min Act: -0.1700

Data Index: 6112817 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1076. Min Act: -0.1700

Data Index: 5946949 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.1116. Min Act: -0.1700

Data Index: 8191618 (Open Web Text)

Max Activating Token Index: 308

Text #17

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.0866. Min Act: -0.1700

Data Index: 5852135 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.0914. Min Act: -0.1700

Data Index: 1894909 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 4.4653. Min Range: -4.4653

Max Act: 4.0563. Min Act: -0.1700

Data Index: 5112987 (Open Web Text)

Max Activating Token Index: 435