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

Dataset: Open Web Text

Neuron 241 in Layer 0

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: 4.1475. Min Range: -4.1475

Max Act: 4.1475. Min Act: -0.1700

Data Index: 6986521 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.1025. Min Act: -0.1700

Data Index: 6162352 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0918. Min Act: -0.1700

Data Index: 6742840 (Open Web Text)

Max Activating Token Index: 321

Text #3

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0372. Min Act: -0.1700

Data Index: 6993612 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0032. Min Act: -0.1700

Data Index: 6077255 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0093. Min Act: -0.1700

Data Index: 3772153 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0113. Min Act: -0.1700

Data Index: 5800791 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0236. Min Act: -0.1700

Data Index: 6892524 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0202. Min Act: -0.1700

Data Index: 6201565 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0025. Min Act: -0.1700

Data Index: 1784363 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9833. Min Act: -0.1700

Data Index: 2652431 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9905. Min Act: -0.1700

Data Index: 711068 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9955. Min Act: -0.1700

Data Index: 4776350 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9953. Min Act: -0.1700

Data Index: 693430 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 4.1475. Min Range: -4.1475

Max Act: 4.0116. Min Act: -0.1700

Data Index: 1245382 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9893. Min Act: -0.1700

Data Index: 4019572 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9793. Min Act: -0.1700

Data Index: 3512440 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9813. Min Act: -0.1700

Data Index: 5944874 (Open Web Text)

Max Activating Token Index: 388

Text #18

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9532. Min Act: -0.1700

Data Index: 5936260 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 4.1475. Min Range: -4.1475

Max Act: 3.9586. Min Act: -0.1700

Data Index: 1670720 (Open Web Text)

Max Activating Token Index: 770