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

Dataset: Open Web Text

Neuron 1848 in Layer 3

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: 5.2733. Min Range: -5.2733

Max Act: 5.2733. Min Act: -0.1700

Data Index: 5025395 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0857. Min Act: -0.1700

Data Index: 7226664 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0364. Min Act: -0.1691

Data Index: 3027283 (Open Web Text)

Max Activating Token Index: 735

Text #3

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9710. Min Act: -0.1700

Data Index: 7814913 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0406. Min Act: -0.1700

Data Index: 8794286 (Open Web Text)

Max Activating Token Index: 776

Text #5

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0450. Min Act: -0.1700

Data Index: 3180259 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9776. Min Act: -0.1700

Data Index: 433104 (Open Web Text)

Max Activating Token Index: 569

Text #7

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9453. Min Act: -0.1700

Data Index: 6610312 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9338. Min Act: -0.1700

Data Index: 1371899 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0523. Min Act: -0.1700

Data Index: 4916087 (Open Web Text)

Max Activating Token Index: 793

Text #10

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8823. Min Act: -0.1700

Data Index: 3357982 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9486. Min Act: -0.1700

Data Index: 8021273 (Open Web Text)

Max Activating Token Index: 334

Text #12

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.0512. Min Act: -0.1700

Data Index: 2315601 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9040. Min Act: -0.1700

Data Index: 3907245 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8322. Min Act: -0.1696

Data Index: 238387 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8176. Min Act: -0.1700

Data Index: 2984208 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8708. Min Act: -0.1700

Data Index: 6051463 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8332. Min Act: -0.1700

Data Index: 5590455 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.8168. Min Act: -0.1700

Data Index: 2958777 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.9157. Min Act: -0.1699

Data Index: 1986088 (Open Web Text)

Max Activating Token Index: 387