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

Dataset: Open Web Text

Neuron 2003 in Layer 1

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: 1.7807. Min Range: -1.7807

Max Act: 1.7807. Min Act: -0.1700

Data Index: 6636145 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7787. Min Act: -0.1700

Data Index: 2766417 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7752. Min Act: -0.1700

Data Index: 2766419 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7609. Min Act: -0.1700

Data Index: 5896451 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7486. Min Act: -0.1700

Data Index: 6097777 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7415. Min Act: -0.1700

Data Index: 7870282 (Open Web Text)

Max Activating Token Index: 266

Text #6

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7320. Min Act: -0.1700

Data Index: 2452005 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7190. Min Act: -0.1700

Data Index: 7636491 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7261. Min Act: -0.1700

Data Index: 2523972 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7252. Min Act: -0.1699

Data Index: 5422138 (Open Web Text)

Max Activating Token Index: 195

Text #10

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7272. Min Act: -0.1700

Data Index: 8559103 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7209. Min Act: -0.1700

Data Index: 1561854 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7184. Min Act: -0.1700

Data Index: 2827759 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7132. Min Act: -0.1700

Data Index: 279761 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7189. Min Act: -0.1700

Data Index: 5858088 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7118. Min Act: -0.1700

Data Index: 1672692 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7085. Min Act: -0.1700

Data Index: 5015534 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.7075. Min Act: -0.1700

Data Index: 2177800 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.6983. Min Act: -0.1700

Data Index: 6538338 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 1.7807. Min Range: -1.7807

Max Act: 1.6963. Min Act: -0.1700

Data Index: 6990358 (Open Web Text)

Max Activating Token Index: 26