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

Dataset: Open Web Text

Neuron 2312 in Layer 5

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: 4.0636. Min Range: -4.0636

Max Act: 4.0636. Min Act: -0.1700

Data Index: 581013 (Open Web Text)

Max Activating Token Index: 785

Text #1

Max Range: 4.0636. Min Range: -4.0636

Max Act: 4.0200. Min Act: -0.1700

Data Index: 5280542 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 4.0636. Min Range: -4.0636

Max Act: 4.0073. Min Act: -0.1700

Data Index: 3963020 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 4.0636. Min Range: -4.0636

Max Act: 4.0182. Min Act: -0.1700

Data Index: 2337587 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9928. Min Act: -0.1700

Data Index: 3319316 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9846. Min Act: -0.1700

Data Index: 7745643 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9948. Min Act: -0.1700

Data Index: 1480264 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9777. Min Act: -0.1700

Data Index: 1152411 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9779. Min Act: -0.1700

Data Index: 8205776 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9735. Min Act: -0.1700

Data Index: 3147658 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9897. Min Act: -0.1700

Data Index: 1850599 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9955. Min Act: -0.1700

Data Index: 8662762 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9533. Min Act: -0.1700

Data Index: 2123779 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9602. Min Act: -0.1700

Data Index: 7565019 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9193. Min Act: -0.1700

Data Index: 2918241 (Open Web Text)

Max Activating Token Index: 830

Text #15

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9569. Min Act: -0.1700

Data Index: 2175288 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9638. Min Act: -0.1700

Data Index: 4071281 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9539. Min Act: -0.1700

Data Index: 8558591 (Open Web Text)

Max Activating Token Index: 284

Text #18

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9685. Min Act: -0.1700

Data Index: 60126 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 4.0636. Min Range: -4.0636

Max Act: 3.9388. Min Act: -0.1700

Data Index: 5131265 (Open Web Text)

Max Activating Token Index: 418