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

Dataset: Open Web Text

Neuron 2264 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: 3.9615. Min Range: -3.9615

Max Act: 3.9615. Min Act: -0.1700

Data Index: 3659380 (Open Web Text)

Max Activating Token Index: 289

Text #1

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.9296. Min Act: -0.1700

Data Index: 4620243 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.9055. Min Act: -0.1700

Data Index: 4084604 (Open Web Text)

Max Activating Token Index: 266

Text #3

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.9128. Min Act: -0.1700

Data Index: 3659387 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8947. Min Act: -0.1700

Data Index: 5126254 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8764. Min Act: -0.1700

Data Index: 5515726 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8537. Min Act: -0.1700

Data Index: 3362984 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8343. Min Act: -0.1700

Data Index: 5126253 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8235. Min Act: -0.1700

Data Index: 5022212 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8135. Min Act: -0.1700

Data Index: 7339441 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7961. Min Act: -0.1700

Data Index: 1882012 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.8113. Min Act: -0.1700

Data Index: 6007953 (Open Web Text)

Max Activating Token Index: 821

Text #12

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7864. Min Act: -0.1700

Data Index: 3507347 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7549. Min Act: -0.1700

Data Index: 4248356 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7753. Min Act: -0.1700

Data Index: 1219405 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7516. Min Act: -0.1700

Data Index: 4620241 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7902. Min Act: -0.1700

Data Index: 4919844 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7974. Min Act: -0.1700

Data Index: 3060304 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7874. Min Act: -0.1700

Data Index: 6188336 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 3.9615. Min Range: -3.9615

Max Act: 3.7457. Min Act: -0.1700

Data Index: 3719046 (Open Web Text)

Max Activating Token Index: 317