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

Dataset: Open Web Text

Neuron 2671 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: 5.2198. Min Range: -5.2198

Max Act: 5.2198. Min Act: -0.1700

Data Index: 1927623 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.1526. Min Act: -0.1700

Data Index: 4570380 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0834. Min Act: -0.1700

Data Index: 7086884 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0149. Min Act: -0.1700

Data Index: 7394036 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0467. Min Act: -0.1700

Data Index: 2655860 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0430. Min Act: -0.1700

Data Index: 8687604 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0088. Min Act: -0.1700

Data Index: 1069721 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0509. Min Act: -0.1700

Data Index: 345262 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 5.2198. Min Range: -5.2198

Max Act: 4.9920. Min Act: -0.1700

Data Index: 385336 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0036. Min Act: -0.1700

Data Index: 7625974 (Open Web Text)

Max Activating Token Index: 47

Text #10

Max Range: 5.2198. Min Range: -5.2198

Max Act: 4.9979. Min Act: -0.1700

Data Index: 6209124 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0320. Min Act: -0.1700

Data Index: 1634382 (Open Web Text)

Max Activating Token Index: 595

Text #12

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0203. Min Act: -0.1700

Data Index: 1569641 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 5.2198. Min Range: -5.2198

Max Act: 4.9965. Min Act: -0.1700

Data Index: 4875472 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 5.2198. Min Range: -5.2198

Max Act: 4.9807. Min Act: -0.1700

Data Index: 4869257 (Open Web Text)

Max Activating Token Index: 701

Text #15

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0171. Min Act: -0.1700

Data Index: 4147546 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0049. Min Act: -0.1700

Data Index: 3678048 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0089. Min Act: -0.1700

Data Index: 1424696 (Open Web Text)

Max Activating Token Index: 642

Text #18

Max Range: 5.2198. Min Range: -5.2198

Max Act: 4.9934. Min Act: -0.1700

Data Index: 7569396 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 5.2198. Min Range: -5.2198

Max Act: 5.0067. Min Act: -0.1700

Data Index: 3351667 (Open Web Text)

Max Activating Token Index: 630