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

Dataset: Open Web Text

Neuron 317 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: 4.0957. Min Range: -4.0957

Max Act: 4.0926. Min Act: -0.1700

Data Index: 7108141 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0957. Min Act: -0.1700

Data Index: 6926245 (Open Web Text)

Max Activating Token Index: 840

Text #2

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0296. Min Act: -0.1700

Data Index: 7800158 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0512. Min Act: -0.1700

Data Index: 1890286 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0289. Min Act: -0.1700

Data Index: 1312131 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0243. Min Act: -0.1700

Data Index: 1397147 (Open Web Text)

Max Activating Token Index: 882

Text #6

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0512. Min Act: -0.1700

Data Index: 1593248 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0557. Min Act: -0.1700

Data Index: 3253050 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0425. Min Act: -0.1700

Data Index: 6803765 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0926. Min Act: -0.1700

Data Index: 483641 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0194. Min Act: -0.1700

Data Index: 4470264 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9931. Min Act: -0.1700

Data Index: 1862776 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0062. Min Act: -0.1700

Data Index: 4180359 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9831. Min Act: -0.1700

Data Index: 7152137 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0234. Min Act: -0.1700

Data Index: 2009510 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9888. Min Act: -0.1700

Data Index: 6038327 (Open Web Text)

Max Activating Token Index: 513

Text #16

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9991. Min Act: -0.1700

Data Index: 4011798 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9834. Min Act: -0.1700

Data Index: 4524118 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 4.0957. Min Range: -4.0957

Max Act: 3.9777. Min Act: -0.1700

Data Index: 814572 (Open Web Text)

Max Activating Token Index: 791

Text #19

Max Range: 4.0957. Min Range: -4.0957

Max Act: 4.0238. Min Act: -0.1700

Data Index: 5374347 (Open Web Text)

Max Activating Token Index: 160