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

Dataset: Open Web Text

Neuron 3066 in Layer 5

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: 3.8780. Min Range: -3.8780

Max Act: 3.8780. Min Act: -0.1700

Data Index: 2297267 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.8633. Min Act: -0.1700

Data Index: 8748322 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.8356. Min Act: -0.1700

Data Index: 1934210 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.8403. Min Act: -0.1700

Data Index: 7084053 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7717. Min Act: -0.1700

Data Index: 3447089 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7710. Min Act: -0.1700

Data Index: 3696472 (Open Web Text)

Max Activating Token Index: 179

Text #6

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7663. Min Act: -0.1700

Data Index: 2429592 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7660. Min Act: -0.1700

Data Index: 245648 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7735. Min Act: -0.1700

Data Index: 7310411 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7498. Min Act: -0.1700

Data Index: 1071432 (Open Web Text)

Max Activating Token Index: 882

Text #10

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7509. Min Act: -0.1700

Data Index: 7568165 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7539. Min Act: -0.1700

Data Index: 1762586 (Open Web Text)

Max Activating Token Index: 800

Text #12

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7481. Min Act: -0.1700

Data Index: 8206195 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7489. Min Act: -0.1700

Data Index: 2888471 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7294. Min Act: -0.1700

Data Index: 8789827 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7498. Min Act: -0.1700

Data Index: 371414 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7024. Min Act: -0.1700

Data Index: 731391 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7216. Min Act: -0.1700

Data Index: 5124262 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.6893. Min Act: -0.1700

Data Index: 3747676 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 3.8780. Min Range: -3.8780

Max Act: 3.7170. Min Act: -0.1700

Data Index: 7261681 (Open Web Text)

Max Activating Token Index: 46