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

Dataset: Open Web Text

Neuron 1271 in Layer 2

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: 3.2657. Min Range: -3.2657

Max Act: 3.2657. Min Act: -0.1700

Data Index: 954333 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2429. Min Act: -0.1700

Data Index: 7325015 (Open Web Text)

Max Activating Token Index: 549

Text #2

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2024. Min Act: -0.1700

Data Index: 2353673 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1978. Min Act: -0.1700

Data Index: 7060959 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1341. Min Act: -0.1700

Data Index: 5240280 (Open Web Text)

Max Activating Token Index: 405

Text #5

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1691. Min Act: -0.1700

Data Index: 3617126 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1316. Min Act: -0.1700

Data Index: 2225432 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1180. Min Act: -0.1700

Data Index: 1418155 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1252. Min Act: -0.1700

Data Index: 4565702 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1007. Min Act: -0.1700

Data Index: 102328 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0925. Min Act: -0.1700

Data Index: 4910893 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0972. Min Act: -0.1700

Data Index: 8416814 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1197. Min Act: -0.1700

Data Index: 6786447 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1053. Min Act: -0.1700

Data Index: 2772819 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0854. Min Act: -0.1700

Data Index: 8670105 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0962. Min Act: -0.1700

Data Index: 977315 (Open Web Text)

Max Activating Token Index: 101

Text #16

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0856. Min Act: -0.1700

Data Index: 800568 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0868. Min Act: -0.1700

Data Index: 7468377 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0891. Min Act: -0.1700

Data Index: 4486508 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0872. Min Act: -0.1700

Data Index: 7244375 (Open Web Text)

Max Activating Token Index: 598