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

Dataset: Open Web Text

Neuron 2915 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: 4.2174. Min Range: -4.2174

Max Act: 4.2031. Min Act: -0.1700

Data Index: 8318261 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.1685. Min Act: -0.1700

Data Index: 5660315 (Open Web Text)

Max Activating Token Index: 160

Text #2

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.2174. Min Act: -0.1700

Data Index: 3935202 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.1510. Min Act: -0.1700

Data Index: 3199486 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0971. Min Act: -0.1700

Data Index: 423511 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.1051. Min Act: -0.1700

Data Index: 2971973 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0929. Min Act: -0.1700

Data Index: 2170698 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0388. Min Act: -0.1700

Data Index: 891319 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0600. Min Act: -0.1700

Data Index: 6836346 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0400. Min Act: -0.1700

Data Index: 7888503 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0103. Min Act: -0.1700

Data Index: 8454758 (Open Web Text)

Max Activating Token Index: 508

Text #11

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.1066. Min Act: -0.1700

Data Index: 6734849 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0444. Min Act: -0.1700

Data Index: 2463858 (Open Web Text)

Max Activating Token Index: 749

Text #13

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9038. Min Act: -0.1700

Data Index: 1642377 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 4.2174. Min Range: -4.2174

Max Act: 4.0423. Min Act: -0.1700

Data Index: 8221616 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9715. Min Act: -0.1700

Data Index: 2336500 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9492. Min Act: -0.1700

Data Index: 1669332 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9884. Min Act: -0.1700

Data Index: 5137348 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9928. Min Act: -0.1700

Data Index: 8019352 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 4.2174. Min Range: -4.2174

Max Act: 3.9578. Min Act: -0.1700

Data Index: 8091985 (Open Web Text)

Max Activating Token Index: 412