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

Dataset: Open Web Text

Neuron 2450 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: 3.0341. Min Range: -3.0341

Max Act: 3.0341. Min Act: -0.1700

Data Index: 882007 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.0341. Min Range: -3.0341

Max Act: 3.0278. Min Act: -0.1700

Data Index: 3978579 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.9993. Min Act: -0.1700

Data Index: 8636995 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.9730. Min Act: -0.1700

Data Index: 1015870 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8955. Min Act: -0.1700

Data Index: 7413062 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8700. Min Act: -0.1700

Data Index: 5234031 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8685. Min Act: -0.1700

Data Index: 8461458 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8630. Min Act: -0.1700

Data Index: 2860551 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8480. Min Act: -0.1700

Data Index: 8793316 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8107. Min Act: -0.1700

Data Index: 3088013 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8266. Min Act: -0.1700

Data Index: 5243498 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8068. Min Act: -0.1700

Data Index: 6618025 (Open Web Text)

Max Activating Token Index: 450

Text #12

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8175. Min Act: -0.1700

Data Index: 2881974 (Open Web Text)

Max Activating Token Index: 928

Text #13

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8190. Min Act: -0.1700

Data Index: 4391837 (Open Web Text)

Max Activating Token Index: 556

Text #14

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8308. Min Act: -0.1700

Data Index: 47021 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8119. Min Act: -0.1700

Data Index: 626308 (Open Web Text)

Max Activating Token Index: 391

Text #16

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.8028. Min Act: -0.1700

Data Index: 7152738 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.7666. Min Act: -0.1700

Data Index: 5548923 (Open Web Text)

Max Activating Token Index: 827

Text #18

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.7834. Min Act: -0.1700

Data Index: 2777516 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 3.0341. Min Range: -3.0341

Max Act: 2.7797. Min Act: -0.1700

Data Index: 6002548 (Open Web Text)

Max Activating Token Index: 48