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

Dataset: Open Web Text

Neuron 2115 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: 4.9218. Min Range: -4.9218

Max Act: 4.9218. Min Act: -0.1700

Data Index: 7379325 (Open Web Text)

Max Activating Token Index: 801

Text #1

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.8640. Min Act: -0.1700

Data Index: 4021969 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.8497. Min Act: -0.1700

Data Index: 5212314 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.8539. Min Act: -0.1700

Data Index: 8096282 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.8461. Min Act: -0.1700

Data Index: 2999443 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7858. Min Act: -0.1700

Data Index: 3794341 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7906. Min Act: -0.1700

Data Index: 5418746 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7630. Min Act: -0.1700

Data Index: 1784789 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7789. Min Act: -0.1700

Data Index: 8515259 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7498. Min Act: -0.1700

Data Index: 4611013 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7642. Min Act: -0.1700

Data Index: 8074613 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7031. Min Act: -0.1700

Data Index: 320757 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7233. Min Act: -0.1700

Data Index: 2712949 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7562. Min Act: -0.1700

Data Index: 3874304 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7184. Min Act: -0.1700

Data Index: 4612116 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7218. Min Act: -0.1700

Data Index: 1870040 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7063. Min Act: -0.1700

Data Index: 1859834 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7267. Min Act: -0.1700

Data Index: 969920 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.6979. Min Act: -0.1700

Data Index: 2829365 (Open Web Text)

Max Activating Token Index: 818

Text #19

Max Range: 4.9218. Min Range: -4.9218

Max Act: 4.7285. Min Act: -0.1700

Data Index: 5492203 (Open Web Text)

Max Activating Token Index: 714