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

Dataset: Open Web Text

Neuron 282 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: 4.3124. Min Range: -4.3124

Max Act: 4.3124. Min Act: -0.1700

Data Index: 1619747 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.2558. Min Act: -0.1700

Data Index: 4216714 (Open Web Text)

Max Activating Token Index: 85

Text #2

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.2385. Min Act: -0.1700

Data Index: 971092 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.2059. Min Act: -0.1700

Data Index: 4947684 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.2272. Min Act: -0.1700

Data Index: 4032758 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1955. Min Act: -0.1700

Data Index: 5401361 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1908. Min Act: -0.1700

Data Index: 304174 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1673. Min Act: -0.1700

Data Index: 3629332 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1413. Min Act: -0.1700

Data Index: 8504780 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1669. Min Act: -0.1700

Data Index: 7815070 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1390. Min Act: -0.1700

Data Index: 2096201 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1608. Min Act: -0.1700

Data Index: 6198368 (Open Web Text)

Max Activating Token Index: 522

Text #12

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1598. Min Act: -0.1700

Data Index: 2363137 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1617. Min Act: -0.1700

Data Index: 4388462 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1553. Min Act: -0.1700

Data Index: 5923382 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1418. Min Act: -0.1700

Data Index: 1222195 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1667. Min Act: -0.1700

Data Index: 5831081 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1528. Min Act: -0.1700

Data Index: 626909 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1542. Min Act: -0.1700

Data Index: 4844845 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.3124. Min Range: -4.3124

Max Act: 4.1049. Min Act: -0.1700

Data Index: 2130931 (Open Web Text)

Max Activating Token Index: 752