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

Dataset: Open Web Text

Neuron 978 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: 3.2224. Min Range: -3.2224

Max Act: 3.2224. Min Act: -0.1700

Data Index: 4209788 (Open Web Text)

Max Activating Token Index: 847

Text #1

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1319. Min Act: -0.1700

Data Index: 7033131 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1497. Min Act: -0.1700

Data Index: 4209787 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.1298. Min Act: -0.1700

Data Index: 6351298 (Open Web Text)

Max Activating Token Index: 910

Text #4

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0931. Min Act: -0.1700

Data Index: 4209786 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0543. Min Act: -0.1700

Data Index: 8828273 (Open Web Text)

Max Activating Token Index: 449

Text #6

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0572. Min Act: -0.1700

Data Index: 4638333 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0547. Min Act: -0.1700

Data Index: 4209789 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.0067. Min Act: -0.1700

Data Index: 4920333 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9846. Min Act: -0.1700

Data Index: 8000381 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9739. Min Act: -0.1700

Data Index: 287859 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9747. Min Act: -0.1700

Data Index: 7431924 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9793. Min Act: -0.1700

Data Index: 5631852 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9933. Min Act: -0.1700

Data Index: 3976108 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9907. Min Act: -0.1700

Data Index: 4920338 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9557. Min Act: -0.1700

Data Index: 313727 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9560. Min Act: -0.1700

Data Index: 5266220 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9590. Min Act: -0.1700

Data Index: 4309102 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9613. Min Act: -0.1700

Data Index: 3460233 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9626. Min Act: -0.1700

Data Index: 3378923 (Open Web Text)

Max Activating Token Index: 946