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

Dataset: Open Web Text

Neuron 2417 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: 4.8286. Min Range: -4.8286

Max Act: 4.8286. Min Act: -0.1700

Data Index: 8538048 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.6899. Min Act: -0.1700

Data Index: 6478687 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.7025. Min Act: -0.1700

Data Index: 2915158 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.5478. Min Act: -0.1700

Data Index: 3422396 (Open Web Text)

Max Activating Token Index: 888

Text #4

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.3838. Min Act: -0.1700

Data Index: 6626892 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.3278. Min Act: -0.1700

Data Index: 7003044 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.3812. Min Act: -0.1700

Data Index: 2975269 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.3147. Min Act: -0.1700

Data Index: 626212 (Open Web Text)

Max Activating Token Index: 845

Text #8

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2946. Min Act: -0.1700

Data Index: 1256327 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2759. Min Act: -0.1700

Data Index: 8647994 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2525. Min Act: -0.1700

Data Index: 3614649 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2457. Min Act: -0.1700

Data Index: 7488273 (Open Web Text)

Max Activating Token Index: 541

Text #12

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2769. Min Act: -0.1700

Data Index: 237251 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.1738. Min Act: -0.1700

Data Index: 5080290 (Open Web Text)

Max Activating Token Index: 676

Text #14

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2085. Min Act: -0.1700

Data Index: 632033 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.2118. Min Act: -0.1700

Data Index: 2520352 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.1827. Min Act: -0.1700

Data Index: 6413665 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.1540. Min Act: -0.1700

Data Index: 1538391 (Open Web Text)

Max Activating Token Index: 365

Text #18

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.1560. Min Act: -0.1700

Data Index: 4278465 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 4.8286. Min Range: -4.8286

Max Act: 4.1602. Min Act: -0.1700

Data Index: 3136454 (Open Web Text)

Max Activating Token Index: 994