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

Dataset: Open Web Text

Neuron 960 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: 4.6077. Min Range: -4.6077

Max Act: 4.6077. Min Act: -0.1700

Data Index: 287013 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.5803. Min Act: -0.1700

Data Index: 3757957 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.4541. Min Act: -0.1700

Data Index: 2065468 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.4647. Min Act: -0.1700

Data Index: 4059672 (Open Web Text)

Max Activating Token Index: 89

Text #4

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.4219. Min Act: -0.1700

Data Index: 1299580 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.4385. Min Act: -0.1700

Data Index: 296176 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3767. Min Act: -0.1700

Data Index: 1744991 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.4348. Min Act: -0.1700

Data Index: 6644882 (Open Web Text)

Max Activating Token Index: 815

Text #8

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3784. Min Act: -0.1700

Data Index: 7750203 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3472. Min Act: -0.1700

Data Index: 8195414 (Open Web Text)

Max Activating Token Index: 89

Text #10

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3779. Min Act: -0.1700

Data Index: 4704783 (Open Web Text)

Max Activating Token Index: 348

Text #11

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3526. Min Act: -0.1700

Data Index: 3951249 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3645. Min Act: -0.1700

Data Index: 8353765 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3223. Min Act: -0.1700

Data Index: 4734179 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3295. Min Act: -0.1700

Data Index: 6973101 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3012. Min Act: -0.1700

Data Index: 8375262 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.2973. Min Act: -0.1700

Data Index: 8467590 (Open Web Text)

Max Activating Token Index: 914

Text #17

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3042. Min Act: -0.1700

Data Index: 759504 (Open Web Text)

Max Activating Token Index: 897

Text #18

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.3147. Min Act: -0.1700

Data Index: 777527 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 4.6077. Min Range: -4.6077

Max Act: 4.2361. Min Act: -0.1700

Data Index: 2846794 (Open Web Text)

Max Activating Token Index: 760