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

Dataset: Open Web Text

Neuron 1047 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: 4.2996. Min Range: -4.2996

Max Act: 4.2796. Min Act: -0.1700

Data Index: 5973259 (Open Web Text)

Max Activating Token Index: 936

Text #1

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.2996. Min Act: -0.1700

Data Index: 5748577 (Open Web Text)

Max Activating Token Index: 954

Text #2

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1822. Min Act: -0.1700

Data Index: 5067057 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1864. Min Act: -0.1700

Data Index: 4982624 (Open Web Text)

Max Activating Token Index: 327

Text #4

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1940. Min Act: -0.1700

Data Index: 2234487 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1922. Min Act: -0.1700

Data Index: 3218943 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1563. Min Act: -0.1700

Data Index: 6399181 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1597. Min Act: -0.1700

Data Index: 6216897 (Open Web Text)

Max Activating Token Index: 391

Text #8

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1623. Min Act: -0.1700

Data Index: 4554681 (Open Web Text)

Max Activating Token Index: 543

Text #9

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1724. Min Act: -0.1700

Data Index: 4502683 (Open Web Text)

Max Activating Token Index: 305

Text #10

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1561. Min Act: -0.1700

Data Index: 1128053 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1297. Min Act: -0.1700

Data Index: 1436296 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1409. Min Act: -0.1700

Data Index: 5327398 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1681. Min Act: -0.1700

Data Index: 1614014 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1672. Min Act: -0.1700

Data Index: 3092288 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1489. Min Act: -0.1700

Data Index: 5294979 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1496. Min Act: -0.1700

Data Index: 5189464 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1575. Min Act: -0.1700

Data Index: 2578131 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1666. Min Act: -0.1700

Data Index: 1552999 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 4.2996. Min Range: -4.2996

Max Act: 4.1763. Min Act: -0.1700

Data Index: 1458593 (Open Web Text)

Max Activating Token Index: 445