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

Dataset: Open Web Text

Neuron 730 in Layer 6

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: 4.2601. Min Range: -4.2601

Max Act: 4.2601. Min Act: -0.1700

Data Index: 8742852 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1845. Min Act: -0.1700

Data Index: 564748 (Open Web Text)

Max Activating Token Index: 898

Text #2

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1692. Min Act: -0.1700

Data Index: 570932 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1631. Min Act: -0.1700

Data Index: 4219566 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1281. Min Act: -0.1700

Data Index: 4564543 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1455. Min Act: -0.1700

Data Index: 7763000 (Open Web Text)

Max Activating Token Index: 846

Text #6

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1402. Min Act: -0.1700

Data Index: 1768197 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1261. Min Act: -0.1700

Data Index: 4168520 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1178. Min Act: -0.1700

Data Index: 2795107 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1149. Min Act: -0.1700

Data Index: 8090216 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1070. Min Act: -0.1700

Data Index: 7580932 (Open Web Text)

Max Activating Token Index: 789

Text #11

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0579. Min Act: -0.1700

Data Index: 2231207 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0831. Min Act: -0.1700

Data Index: 1127377 (Open Web Text)

Max Activating Token Index: 240

Text #13

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0943. Min Act: -0.1700

Data Index: 2290835 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0922. Min Act: -0.1700

Data Index: 2291872 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0977. Min Act: -0.1700

Data Index: 5951231 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0641. Min Act: -0.1700

Data Index: 2388522 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0902. Min Act: -0.1700

Data Index: 4758216 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.0885. Min Act: -0.1700

Data Index: 12141 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 4.2601. Min Range: -4.2601

Max Act: 4.1198. Min Act: -0.1700

Data Index: 8079719 (Open Web Text)

Max Activating Token Index: 653