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

Dataset: Open Web Text

Neuron 962 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: 3.6328. Min Range: -3.6328

Max Act: 3.6328. Min Act: -0.1700

Data Index: 4695564 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.3696. Min Act: -0.1700

Data Index: 889959 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.3616. Min Act: -0.1700

Data Index: 6591637 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.3700. Min Act: -0.1700

Data Index: 3209934 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.3283. Min Act: -0.1700

Data Index: 8463014 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2228. Min Act: -0.1700

Data Index: 7706556 (Open Web Text)

Max Activating Token Index: 884

Text #6

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2842. Min Act: -0.1700

Data Index: 7573198 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2630. Min Act: -0.1700

Data Index: 3044571 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2731. Min Act: -0.1700

Data Index: 4912148 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2642. Min Act: -0.1700

Data Index: 3509017 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2052. Min Act: -0.1700

Data Index: 5194989 (Open Web Text)

Max Activating Token Index: 730

Text #11

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2461. Min Act: -0.1700

Data Index: 5410239 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2196. Min Act: -0.1700

Data Index: 789212 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2538. Min Act: -0.1700

Data Index: 154450 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.2073. Min Act: -0.1700

Data Index: 4024395 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.1923. Min Act: -0.1700

Data Index: 1304489 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.1896. Min Act: -0.1700

Data Index: 5014429 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.1879. Min Act: -0.1700

Data Index: 286560 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.1811. Min Act: -0.1700

Data Index: 4054637 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 3.6328. Min Range: -3.6328

Max Act: 3.1693. Min Act: -0.1700

Data Index: 4028224 (Open Web Text)

Max Activating Token Index: 454