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

Dataset: Open Web Text

Neuron 863 in Layer 6

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: 4.3082. Min Range: -4.3082

Max Act: 4.3082. Min Act: -0.1700

Data Index: 6391064 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.2542. Min Act: -0.1700

Data Index: 5533629 (Open Web Text)

Max Activating Token Index: 735

Text #2

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.2068. Min Act: -0.1700

Data Index: 5197894 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.2579. Min Act: -0.1700

Data Index: 8044011 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.1957. Min Act: -0.1700

Data Index: 5911262 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.1587. Min Act: -0.1700

Data Index: 718286 (Open Web Text)

Max Activating Token Index: 461

Text #6

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.1401. Min Act: -0.1700

Data Index: 3030079 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.1067. Min Act: -0.1700

Data Index: 974482 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0975. Min Act: -0.1700

Data Index: 7150815 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0895. Min Act: -0.1700

Data Index: 39791 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0738. Min Act: -0.1700

Data Index: 3537383 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0478. Min Act: -0.1700

Data Index: 4644591 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0585. Min Act: -0.1700

Data Index: 8795049 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0364. Min Act: -0.1700

Data Index: 3773650 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0305. Min Act: -0.1700

Data Index: 6579003 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0036. Min Act: -0.1700

Data Index: 7779836 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 4.3082. Min Range: -4.3082

Max Act: 3.9986. Min Act: -0.1700

Data Index: 6057025 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0106. Min Act: -0.1700

Data Index: 7108343 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 4.3082. Min Range: -4.3082

Max Act: 4.0169. Min Act: -0.1700

Data Index: 4646676 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 4.3082. Min Range: -4.3082

Max Act: 3.9778. Min Act: -0.1700

Data Index: 2046052 (Open Web Text)

Max Activating Token Index: 113