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

Dataset: Open Web Text

Neuron 1055 in Layer 6

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: 3.7767. Min Range: -3.7767

Max Act: 3.7767. Min Act: -0.1700

Data Index: 350405 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7256. Min Act: -0.1700

Data Index: 7839267 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7152. Min Act: -0.1700

Data Index: 6776755 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6905. Min Act: -0.1700

Data Index: 5403931 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.7052. Min Act: -0.1700

Data Index: 4055770 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6671. Min Act: -0.1700

Data Index: 552491 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6542. Min Act: -0.1700

Data Index: 6776754 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6672. Min Act: -0.1700

Data Index: 5029198 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6635. Min Act: -0.1700

Data Index: 3359578 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6448. Min Act: -0.1700

Data Index: 5096140 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6657. Min Act: -0.1700

Data Index: 1556247 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6568. Min Act: -0.1700

Data Index: 6174827 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6544. Min Act: -0.1700

Data Index: 1935257 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6507. Min Act: -0.1700

Data Index: 6315452 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6361. Min Act: -0.1700

Data Index: 5556852 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6336. Min Act: -0.1700

Data Index: 7385203 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6112. Min Act: -0.1700

Data Index: 2333567 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.6167. Min Act: -0.1700

Data Index: 3671006 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5948. Min Act: -0.1700

Data Index: 774166 (Open Web Text)

Max Activating Token Index: 948

Text #19

Max Range: 3.7767. Min Range: -3.7767

Max Act: 3.5888. Min Act: -0.1700

Data Index: 2121284 (Open Web Text)

Max Activating Token Index: 797