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

Dataset: Open Web Text

Neuron 2311 in Layer 3

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: 3.1237. Min Range: -3.1237

Max Act: 3.1237. Min Act: -0.1700

Data Index: 6869708 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0994. Min Act: -0.1700

Data Index: 8296234 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0410. Min Act: -0.1700

Data Index: 4378200 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0376. Min Act: -0.1700

Data Index: 288976 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0322. Min Act: -0.1700

Data Index: 6312742 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0235. Min Act: -0.1700

Data Index: 1452642 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9831. Min Act: -0.1700

Data Index: 5780972 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9742. Min Act: -0.1700

Data Index: 8112943 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 3.1237. Min Range: -3.1237

Max Act: 3.0017. Min Act: -0.1700

Data Index: 7634989 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9702. Min Act: -0.1700

Data Index: 5593484 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9615. Min Act: -0.1700

Data Index: 3876205 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9040. Min Act: -0.1700

Data Index: 4284336 (Open Web Text)

Max Activating Token Index: 635

Text #12

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9348. Min Act: -0.1700

Data Index: 2172930 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9502. Min Act: -0.1700

Data Index: 4440370 (Open Web Text)

Max Activating Token Index: 925

Text #14

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9162. Min Act: -0.1700

Data Index: 1883164 (Open Web Text)

Max Activating Token Index: 215

Text #15

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.8998. Min Act: -0.1700

Data Index: 8047483 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9202. Min Act: -0.1700

Data Index: 4214316 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.8462. Min Act: -0.1700

Data Index: 8112287 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.8824. Min Act: -0.1700

Data Index: 1237752 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 3.1237. Min Range: -3.1237

Max Act: 2.9136. Min Act: -0.1700

Data Index: 3207343 (Open Web Text)

Max Activating Token Index: 96