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

Dataset: Open Web Text

Neuron 583 in Layer 2

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: 3.0506. Min Range: -3.0506

Max Act: 3.0506. Min Act: -0.1700

Data Index: 2377143 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.9458. Min Act: -0.1700

Data Index: 4553068 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.9382. Min Act: -0.1700

Data Index: 2825484 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.9146. Min Act: -0.1700

Data Index: 6228091 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.8883. Min Act: -0.1700

Data Index: 4283485 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.8170. Min Act: -0.1700

Data Index: 4954177 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7950. Min Act: -0.1700

Data Index: 1299203 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.8206. Min Act: -0.1700

Data Index: 2743931 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7889. Min Act: -0.1700

Data Index: 2076262 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7696. Min Act: -0.1700

Data Index: 976137 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7863. Min Act: -0.1700

Data Index: 2835086 (Open Web Text)

Max Activating Token Index: 971

Text #11

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7385. Min Act: -0.1700

Data Index: 5750303 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7845. Min Act: -0.1700

Data Index: 2743930 (Open Web Text)

Max Activating Token Index: 613

Text #13

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7486. Min Act: -0.1700

Data Index: 8581569 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7382. Min Act: -0.1700

Data Index: 726588 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.6984. Min Act: -0.1700

Data Index: 6309740 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7223. Min Act: -0.1700

Data Index: 1299214 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.6991. Min Act: -0.1700

Data Index: 4262227 (Open Web Text)

Max Activating Token Index: 563

Text #18

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.6898. Min Act: -0.1700

Data Index: 2303590 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.7009. Min Act: -0.1700

Data Index: 6408300 (Open Web Text)

Max Activating Token Index: 304