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

Dataset: Open Web Text

Neuron 2754 in Layer 1

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: 3.8794. Min Range: -3.8794

Max Act: 3.8794. Min Act: -0.1700

Data Index: 6527958 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.8155. Min Act: -0.1700

Data Index: 4302210 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7881. Min Act: -0.1700

Data Index: 2367486 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7460. Min Act: -0.1700

Data Index: 1052980 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7603. Min Act: -0.1700

Data Index: 6035451 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7418. Min Act: -0.1700

Data Index: 2055706 (Open Web Text)

Max Activating Token Index: 521

Text #6

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7421. Min Act: -0.1700

Data Index: 2535418 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7303. Min Act: -0.1700

Data Index: 862569 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7456. Min Act: -0.1700

Data Index: 7638849 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7062. Min Act: -0.1700

Data Index: 1879547 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7320. Min Act: -0.1700

Data Index: 1591294 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7009. Min Act: -0.1700

Data Index: 3253732 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7094. Min Act: -0.1700

Data Index: 2023581 (Open Web Text)

Max Activating Token Index: 572

Text #13

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7098. Min Act: -0.1700

Data Index: 3998197 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7377. Min Act: -0.1700

Data Index: 365696 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7223. Min Act: -0.1700

Data Index: 4269732 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7331. Min Act: -0.1700

Data Index: 255475 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1420237 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7056. Min Act: -0.1700

Data Index: 5445167 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7044. Min Act: -0.1700

Data Index: 5445166 (Open Web Text)

Max Activating Token Index: 797