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

Dataset: Open Web Text

Neuron 1762 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: 4.8367. Min Range: -4.8367

Max Act: 4.8367. Min Act: -0.1700

Data Index: 1367628 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7894. Min Act: -0.1700

Data Index: 6384569 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7803. Min Act: -0.1700

Data Index: 4691564 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7523. Min Act: -0.1700

Data Index: 6115150 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7454. Min Act: -0.1700

Data Index: 2479386 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7538. Min Act: -0.1700

Data Index: 4740315 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6990. Min Act: -0.1700

Data Index: 121911 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7166. Min Act: -0.1700

Data Index: 6073794 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.7027. Min Act: -0.1700

Data Index: 4268197 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6440. Min Act: -0.1700

Data Index: 5284414 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6787. Min Act: -0.1700

Data Index: 5359701 (Open Web Text)

Max Activating Token Index: 137

Text #11

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6839. Min Act: -0.1700

Data Index: 506029 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6652. Min Act: -0.1700

Data Index: 7174334 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6161. Min Act: -0.1700

Data Index: 8162974 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6210. Min Act: -0.1700

Data Index: 4918198 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6451. Min Act: -0.1700

Data Index: 2170807 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6396. Min Act: -0.1700

Data Index: 927755 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6179. Min Act: -0.1700

Data Index: 4585560 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.6136. Min Act: -0.1700

Data Index: 3801075 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 4.8367. Min Range: -4.8367

Max Act: 4.5921. Min Act: -0.1700

Data Index: 3887036 (Open Web Text)

Max Activating Token Index: 413