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

Dataset: Open Web Text

Neuron 1273 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: 3.8777. Min Range: -3.8777

Max Act: 3.8593. Min Act: -0.1700

Data Index: 2319525 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8761. Min Act: -0.1700

Data Index: 2319545 (Open Web Text)

Max Activating Token Index: 957

Text #2

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8735. Min Act: -0.1700

Data Index: 2319539 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8446. Min Act: -0.1700

Data Index: 8209336 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8498. Min Act: -0.1700

Data Index: 2319548 (Open Web Text)

Max Activating Token Index: 788

Text #5

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8496. Min Act: -0.1700

Data Index: 2319538 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8515. Min Act: -0.1700

Data Index: 2319528 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8777. Min Act: -0.1700

Data Index: 2319535 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8545. Min Act: -0.1700

Data Index: 2319543 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8433. Min Act: -0.1700

Data Index: 2319544 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8260. Min Act: -0.1700

Data Index: 3779094 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8370. Min Act: -0.1700

Data Index: 2319522 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8420. Min Act: -0.1700

Data Index: 2319536 (Open Web Text)

Max Activating Token Index: 459

Text #13

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8211. Min Act: -0.1700

Data Index: 2319526 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8309. Min Act: -0.1700

Data Index: 2319550 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8082. Min Act: -0.1700

Data Index: 2319532 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8028. Min Act: -0.1700

Data Index: 2319529 (Open Web Text)

Max Activating Token Index: 750

Text #17

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7846. Min Act: -0.1700

Data Index: 2319531 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7940. Min Act: -0.1700

Data Index: 2319542 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7970. Min Act: -0.1700

Data Index: 2319541 (Open Web Text)

Max Activating Token Index: 703