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

Dataset: Open Web Text

Neuron 2576 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: 2.3255. Min Range: -2.3255

Max Act: 2.2789. Min Act: -0.1700

Data Index: 4920633 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.3255. Min Act: -0.1700

Data Index: 6718601 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2908. Min Act: -0.1700

Data Index: 8517546 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2720. Min Act: -0.1700

Data Index: 2934838 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2656. Min Act: -0.1700

Data Index: 3437289 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2566. Min Act: -0.1700

Data Index: 1600450 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2740. Min Act: -0.1700

Data Index: 2934312 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2458. Min Act: -0.1700

Data Index: 213995 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2431. Min Act: -0.1700

Data Index: 5682996 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2662. Min Act: -0.1700

Data Index: 4443264 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2616. Min Act: -0.1700

Data Index: 1998373 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2601. Min Act: -0.1700

Data Index: 609152 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2403. Min Act: -0.1700

Data Index: 7061028 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.1931. Min Act: -0.1700

Data Index: 6883707 (Open Web Text)

Max Activating Token Index: 974

Text #14

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.1959. Min Act: -0.1700

Data Index: 7763286 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2318. Min Act: -0.1700

Data Index: 7800715 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2019. Min Act: -0.1700

Data Index: 7643007 (Open Web Text)

Max Activating Token Index: 728

Text #17

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2074. Min Act: -0.1700

Data Index: 2671721 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.2029. Min Act: -0.1700

Data Index: 6234983 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 2.3255. Min Range: -2.3255

Max Act: 2.1868. Min Act: -0.1700

Data Index: 7641166 (Open Web Text)

Max Activating Token Index: 387