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

Dataset: Open Web Text

Neuron 1000 in Layer 4

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: 4.0961. Min Range: -4.0961

Max Act: 4.0961. Min Act: -0.1700

Data Index: 3883499 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7728. Min Act: -0.1700

Data Index: 1631804 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7867. Min Act: -0.1700

Data Index: 4750162 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7304. Min Act: -0.1700

Data Index: 4987723 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7631. Min Act: -0.1700

Data Index: 6001065 (Open Web Text)

Max Activating Token Index: 73

Text #5

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.7150. Min Act: -0.1700

Data Index: 4511299 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6727. Min Act: -0.1700

Data Index: 7452820 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6754. Min Act: -0.1700

Data Index: 3071176 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6592. Min Act: -0.1700

Data Index: 4548479 (Open Web Text)

Max Activating Token Index: 308

Text #9

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6581. Min Act: -0.1700

Data Index: 5155690 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6518. Min Act: -0.1700

Data Index: 8623741 (Open Web Text)

Max Activating Token Index: 565

Text #11

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6595. Min Act: -0.1700

Data Index: 8468388 (Open Web Text)

Max Activating Token Index: 586

Text #12

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.5969. Min Act: -0.1700

Data Index: 45448 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6347. Min Act: -0.1700

Data Index: 817193 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6109. Min Act: -0.1700

Data Index: 3949665 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6382. Min Act: -0.1700

Data Index: 4028341 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6544. Min Act: -0.1700

Data Index: 4838789 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6333. Min Act: -0.1700

Data Index: 2051605 (Open Web Text)

Max Activating Token Index: 625

Text #18

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.6255. Min Act: -0.1700

Data Index: 2106589 (Open Web Text)

Max Activating Token Index: 269

Text #19

Max Range: 4.0961. Min Range: -4.0961

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1323001 (Open Web Text)

Max Activating Token Index: 709