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

Dataset: Open Web Text

Neuron 890 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: 1.8290. Min Range: -1.8290

Max Act: 1.8290. Min Act: -0.1700

Data Index: 3734409 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.8044. Min Act: -0.1700

Data Index: 4281111 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7968. Min Act: -0.1700

Data Index: 1514205 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7803. Min Act: -0.1700

Data Index: 3379305 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7733. Min Act: -0.1700

Data Index: 343097 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7751. Min Act: -0.1700

Data Index: 1500285 (Open Web Text)

Max Activating Token Index: 742

Text #6

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7607. Min Act: -0.1700

Data Index: 1360444 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7509. Min Act: -0.1700

Data Index: 7842245 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7508. Min Act: -0.1700

Data Index: 1899976 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7617. Min Act: -0.1700

Data Index: 3447440 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7384. Min Act: -0.1700

Data Index: 2732695 (Open Web Text)

Max Activating Token Index: 764

Text #11

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7297. Min Act: -0.1700

Data Index: 254885 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7350. Min Act: -0.1700

Data Index: 6002666 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7324. Min Act: -0.1700

Data Index: 5506880 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7150. Min Act: -0.1700

Data Index: 1152411 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.6957. Min Act: -0.1700

Data Index: 6158793 (Open Web Text)

Max Activating Token Index: 949

Text #16

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7068. Min Act: -0.1700

Data Index: 6225876 (Open Web Text)

Max Activating Token Index: 662

Text #17

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7106. Min Act: -0.1700

Data Index: 7817606 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.7043. Min Act: -0.1700

Data Index: 6898637 (Open Web Text)

Max Activating Token Index: 311

Text #19

Max Range: 1.8290. Min Range: -1.8290

Max Act: 1.6966. Min Act: -0.1700

Data Index: 6994809 (Open Web Text)

Max Activating Token Index: 205