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

Dataset: Open Web Text

Neuron 908 in Layer 1

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: 3.3018. Min Range: -3.3018

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1198767 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2783. Min Act: -0.1700

Data Index: 1888904 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2609. Min Act: -0.1700

Data Index: 665658 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2524. Min Act: -0.1700

Data Index: 3291834 (Open Web Text)

Max Activating Token Index: 919

Text #4

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1929. Min Act: -0.1700

Data Index: 7693306 (Open Web Text)

Max Activating Token Index: 253

Text #5

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1907. Min Act: -0.1700

Data Index: 3792138 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1629. Min Act: -0.1700

Data Index: 3006449 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1706. Min Act: -0.1700

Data Index: 4097546 (Open Web Text)

Max Activating Token Index: 221

Text #8

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1533. Min Act: -0.1700

Data Index: 8715156 (Open Web Text)

Max Activating Token Index: 546

Text #9

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1484. Min Act: -0.1700

Data Index: 4310258 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1571. Min Act: -0.1700

Data Index: 1014991 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1579. Min Act: -0.1700

Data Index: 5702279 (Open Web Text)

Max Activating Token Index: 322

Text #12

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1521. Min Act: -0.1700

Data Index: 1621256 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1641. Min Act: -0.1700

Data Index: 8706219 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1602. Min Act: -0.1700

Data Index: 5001058 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1358. Min Act: -0.1700

Data Index: 6966282 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1396. Min Act: -0.1700

Data Index: 2280828 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1490. Min Act: -0.1700

Data Index: 8002083 (Open Web Text)

Max Activating Token Index: 629

Text #18

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1322. Min Act: -0.1700

Data Index: 6774395 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1442. Min Act: -0.1700

Data Index: 355683 (Open Web Text)

Max Activating Token Index: 428