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

Dataset: Open Web Text

Neuron 1479 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: 3.1337. Min Range: -3.1337

Max Act: 3.1337. Min Act: -0.1700

Data Index: 1092134 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 3.1337. Min Range: -3.1337

Max Act: 3.1008. Min Act: -0.1700

Data Index: 3151075 (Open Web Text)

Max Activating Token Index: 406

Text #2

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9461. Min Act: -0.1700

Data Index: 2331253 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9557. Min Act: -0.1700

Data Index: 4524488 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9356. Min Act: -0.1700

Data Index: 1963101 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9652. Min Act: -0.1700

Data Index: 4300523 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9653. Min Act: -0.1700

Data Index: 6424614 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9602. Min Act: -0.1700

Data Index: 7583807 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9158. Min Act: -0.1700

Data Index: 8640995 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9717. Min Act: -0.1700

Data Index: 569765 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9537. Min Act: -0.1700

Data Index: 5670025 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9196. Min Act: -0.1700

Data Index: 4215417 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9046. Min Act: -0.1700

Data Index: 952486 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9368. Min Act: -0.1700

Data Index: 1081755 (Open Web Text)

Max Activating Token Index: 265

Text #14

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9080. Min Act: -0.1700

Data Index: 1410507 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9563. Min Act: -0.1700

Data Index: 1263890 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9154. Min Act: -0.1700

Data Index: 3691265 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9102. Min Act: -0.1700

Data Index: 4771024 (Open Web Text)

Max Activating Token Index: 307

Text #18

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9084. Min Act: -0.1700

Data Index: 8357916 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9022. Min Act: -0.1700

Data Index: 6230801 (Open Web Text)

Max Activating Token Index: 393