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

Dataset: Open Web Text

Neuron 698 in Layer 2

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: 2.1969. Min Range: -2.1969

Max Act: 2.1969. Min Act: -0.1700

Data Index: 8026807 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1696. Min Act: -0.1700

Data Index: 2756372 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1424. Min Act: -0.1700

Data Index: 3405007 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1477. Min Act: -0.1700

Data Index: 2678833 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1276. Min Act: -0.1700

Data Index: 5656695 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1156. Min Act: -0.1700

Data Index: 1122617 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1124. Min Act: -0.1700

Data Index: 4629000 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1188. Min Act: -0.1700

Data Index: 6942135 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.1133. Min Act: -0.1700

Data Index: 4308149 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0955. Min Act: -0.1700

Data Index: 1354782 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0685. Min Act: -0.1700

Data Index: 8670328 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0624. Min Act: -0.1700

Data Index: 4477336 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0562. Min Act: -0.1700

Data Index: 4979679 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0601. Min Act: -0.1700

Data Index: 3540260 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0638. Min Act: -0.1700

Data Index: 434149 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0574. Min Act: -0.1700

Data Index: 6516439 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0540. Min Act: -0.1700

Data Index: 7634857 (Open Web Text)

Max Activating Token Index: 135

Text #17

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0476. Min Act: -0.1700

Data Index: 2409751 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0533. Min Act: -0.1700

Data Index: 7615966 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 2.1969. Min Range: -2.1969

Max Act: 2.0464. Min Act: -0.1700

Data Index: 1669875 (Open Web Text)

Max Activating Token Index: 14