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

Dataset: Open Web Text

Neuron 190 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: 3.6306. Min Range: -3.6306

Max Act: 3.6306. Min Act: -0.1700

Data Index: 8695806 (Open Web Text)

Max Activating Token Index: 880

Text #1

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.6069. Min Act: -0.1700

Data Index: 866610 (Open Web Text)

Max Activating Token Index: 185

Text #2

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.6160. Min Act: -0.1700

Data Index: 2910649 (Open Web Text)

Max Activating Token Index: 192

Text #3

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.6063. Min Act: -0.1700

Data Index: 327162 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5876. Min Act: -0.1700

Data Index: 63605 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5758. Min Act: -0.1700

Data Index: 5629355 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5291. Min Act: -0.1700

Data Index: 101394 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5369. Min Act: -0.1700

Data Index: 8097049 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5329. Min Act: -0.1700

Data Index: 2482118 (Open Web Text)

Max Activating Token Index: 181

Text #9

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5167. Min Act: -0.1700

Data Index: 8605226 (Open Web Text)

Max Activating Token Index: 852

Text #10

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5009. Min Act: -0.1700

Data Index: 5800264 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4784. Min Act: -0.1700

Data Index: 1461341 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.5059. Min Act: -0.1700

Data Index: 2590800 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4793. Min Act: -0.1700

Data Index: 7755522 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4624. Min Act: -0.1700

Data Index: 3338256 (Open Web Text)

Max Activating Token Index: 969

Text #15

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4638. Min Act: -0.1700

Data Index: 6937563 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4564. Min Act: -0.1700

Data Index: 6265640 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4580. Min Act: -0.1700

Data Index: 4150732 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4598. Min Act: -0.1700

Data Index: 2581218 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.6306. Min Range: -3.6306

Max Act: 3.4590. Min Act: -0.1700

Data Index: 7607934 (Open Web Text)

Max Activating Token Index: 324