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

Dataset: Open Web Text

Neuron 1080 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: 4.2247. Min Range: -4.2247

Max Act: 4.2245. Min Act: -0.1700

Data Index: 2179000 (Open Web Text)

Max Activating Token Index: 239

Text #1

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.2247. Min Act: -0.1700

Data Index: 1855197 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.1537. Min Act: -0.1700

Data Index: 1960773 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.1469. Min Act: -0.1700

Data Index: 1671462 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.1355. Min Act: -0.1700

Data Index: 4459887 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.1025. Min Act: -0.1700

Data Index: 7926270 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0990. Min Act: -0.1700

Data Index: 3231553 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0943. Min Act: -0.1700

Data Index: 1436728 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0643. Min Act: -0.1700

Data Index: 2445177 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0841. Min Act: -0.1700

Data Index: 5792607 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0940. Min Act: -0.1700

Data Index: 3531781 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0823. Min Act: -0.1700

Data Index: 4602220 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0758. Min Act: -0.1700

Data Index: 1022693 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0488. Min Act: -0.1700

Data Index: 4313498 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0712. Min Act: -0.1700

Data Index: 1676474 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0440. Min Act: -0.1700

Data Index: 1765517 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0329. Min Act: -0.1700

Data Index: 4974537 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 4.2247. Min Range: -4.2247

Max Act: 3.9924. Min Act: -0.1700

Data Index: 4362072 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0064. Min Act: -0.1700

Data Index: 4967154 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 4.2247. Min Range: -4.2247

Max Act: 4.0149. Min Act: -0.1700

Data Index: 6411756 (Open Web Text)

Max Activating Token Index: 262