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

Dataset: Open Web Text

Neuron 922 in Layer 0

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: 2.5355. Min Range: -2.5355

Max Act: 2.5355. Min Act: -0.1689

Data Index: 1587241 (Open Web Text)

Max Activating Token Index: 270

Text #1

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4675. Min Act: -0.1700

Data Index: 3328161 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4706. Min Act: -0.1695

Data Index: 1587246 (Open Web Text)

Max Activating Token Index: 551

Text #3

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4506. Min Act: -0.1699

Data Index: 6628499 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4336. Min Act: -0.1561

Data Index: 1587243 (Open Web Text)

Max Activating Token Index: 768

Text #5

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4079. Min Act: -0.1700

Data Index: 585382 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4308. Min Act: -0.1700

Data Index: 8119101 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4128. Min Act: -0.1700

Data Index: 6465385 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.4024. Min Act: -0.1700

Data Index: 1243424 (Open Web Text)

Max Activating Token Index: 199

Text #9

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3652. Min Act: -0.1700

Data Index: 6750321 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3769. Min Act: -0.1551

Data Index: 1587242 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3702. Min Act: -0.1700

Data Index: 6274036 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3498. Min Act: -0.1700

Data Index: 4999370 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3402. Min Act: -0.1645

Data Index: 1587245 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3264. Min Act: -0.1700

Data Index: 6506437 (Open Web Text)

Max Activating Token Index: 157

Text #15

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3301. Min Act: -0.1700

Data Index: 2615015 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3155. Min Act: -0.1700

Data Index: 5965264 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3048. Min Act: -0.1700

Data Index: 7082890 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3140. Min Act: -0.1700

Data Index: 2004486 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 2.5355. Min Range: -2.5355

Max Act: 2.3081. Min Act: -0.1700

Data Index: 6190628 (Open Web Text)

Max Activating Token Index: 463