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

Dataset: Open Web Text

Neuron 2546 in Layer 4

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: 2.8468. Min Range: -2.8468

Max Act: 2.8468. Min Act: -0.1700

Data Index: 2596633 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7288. Min Act: -0.1700

Data Index: 6621411 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7229. Min Act: -0.1700

Data Index: 6621409 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7080. Min Act: -0.1700

Data Index: 44262 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7138. Min Act: -0.1700

Data Index: 6621417 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7033. Min Act: -0.1700

Data Index: 7398768 (Open Web Text)

Max Activating Token Index: 416

Text #6

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6658. Min Act: -0.1700

Data Index: 6621418 (Open Web Text)

Max Activating Token Index: 596

Text #7

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7074. Min Act: -0.1700

Data Index: 6621401 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7265. Min Act: -0.1700

Data Index: 6621402 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6953. Min Act: -0.1700

Data Index: 6621413 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7161. Min Act: -0.1700

Data Index: 7398755 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6972. Min Act: -0.1700

Data Index: 44263 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7026. Min Act: -0.1700

Data Index: 44275 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6963. Min Act: -0.1700

Data Index: 7398774 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6908. Min Act: -0.1700

Data Index: 44256 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7144. Min Act: -0.1700

Data Index: 44266 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6666. Min Act: -0.1700

Data Index: 6621406 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6684. Min Act: -0.1700

Data Index: 6621422 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6902. Min Act: -0.1700

Data Index: 5896715 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.7056. Min Act: -0.1700

Data Index: 7398762 (Open Web Text)

Max Activating Token Index: 578