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

Dataset: Open Web Text

Neuron 420 in Layer 5

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: 4.0383. Min Range: -4.0383

Max Act: 4.0383. Min Act: -0.1700

Data Index: 2440886 (Open Web Text)

Max Activating Token Index: 215

Text #1

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9274. Min Act: -0.1700

Data Index: 6548210 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9472. Min Act: -0.1700

Data Index: 6724312 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9490. Min Act: -0.1700

Data Index: 20291 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9553. Min Act: -0.1700

Data Index: 7405725 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9470. Min Act: -0.1700

Data Index: 1221087 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9505. Min Act: -0.1700

Data Index: 2643128 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9116. Min Act: -0.1700

Data Index: 76079 (Open Web Text)

Max Activating Token Index: 699

Text #8

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9177. Min Act: -0.1700

Data Index: 3851599 (Open Web Text)

Max Activating Token Index: 940

Text #9

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9019. Min Act: -0.1700

Data Index: 4867582 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9046. Min Act: -0.1700

Data Index: 3364765 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9202. Min Act: -0.1700

Data Index: 2310788 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9320. Min Act: -0.1700

Data Index: 180954 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.9227. Min Act: -0.1700

Data Index: 5857987 (Open Web Text)

Max Activating Token Index: 249

Text #14

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8897. Min Act: -0.1700

Data Index: 2415879 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8828. Min Act: -0.1700

Data Index: 5931397 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8865. Min Act: -0.1700

Data Index: 5221723 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8914. Min Act: -0.1700

Data Index: 233414 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8879. Min Act: -0.1700

Data Index: 5064519 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 4.0383. Min Range: -4.0383

Max Act: 3.8657. Min Act: -0.1700

Data Index: 1155429 (Open Web Text)

Max Activating Token Index: 662