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

Dataset: Open Web Text

Neuron 1092 in Layer 2

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: 3.9409. Min Range: -3.9409

Max Act: 3.9409. Min Act: -0.1700

Data Index: 6305867 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.7838. Min Act: -0.1700

Data Index: 5557179 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.7500. Min Act: -0.1700

Data Index: 4494090 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.7063. Min Act: -0.1700

Data Index: 6614680 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6453. Min Act: -0.1700

Data Index: 3520032 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6154. Min Act: -0.1700

Data Index: 8088778 (Open Web Text)

Max Activating Token Index: 758

Text #6

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6223. Min Act: -0.1700

Data Index: 4303500 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6435. Min Act: -0.1700

Data Index: 1001095 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6555. Min Act: -0.1700

Data Index: 8325961 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6537. Min Act: -0.1700

Data Index: 1380876 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6197. Min Act: -0.1700

Data Index: 7052193 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6351. Min Act: -0.1700

Data Index: 7398407 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6357. Min Act: -0.1700

Data Index: 2257603 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6223. Min Act: -0.1700

Data Index: 3011305 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6023. Min Act: -0.1700

Data Index: 6035664 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6028. Min Act: -0.1700

Data Index: 4653003 (Open Web Text)

Max Activating Token Index: 223

Text #16

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.5938. Min Act: -0.1700

Data Index: 2623025 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.6018. Min Act: -0.1700

Data Index: 7776523 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.5854. Min Act: -0.1700

Data Index: 3271331 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.5723. Min Act: -0.1700

Data Index: 6728606 (Open Web Text)

Max Activating Token Index: 67