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

Dataset: Open Web Text

Neuron 2594 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: 3.6491. Min Range: -3.6491

Max Act: 3.6328. Min Act: -0.1700

Data Index: 621009 (Open Web Text)

Max Activating Token Index: 262

Text #1

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.6491. Min Act: -0.1700

Data Index: 8538688 (Open Web Text)

Max Activating Token Index: 811

Text #2

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.6319. Min Act: -0.1700

Data Index: 5427036 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5837. Min Act: -0.1700

Data Index: 3814138 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5755. Min Act: -0.1700

Data Index: 3421271 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5315. Min Act: -0.1700

Data Index: 412029 (Open Web Text)

Max Activating Token Index: 992

Text #6

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5395. Min Act: -0.1700

Data Index: 5614759 (Open Web Text)

Max Activating Token Index: 409

Text #7

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5829. Min Act: -0.1700

Data Index: 2190333 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5550. Min Act: -0.1700

Data Index: 6247131 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5276. Min Act: -0.1700

Data Index: 4507454 (Open Web Text)

Max Activating Token Index: 681

Text #10

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5042. Min Act: -0.1700

Data Index: 1997083 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4924. Min Act: -0.1700

Data Index: 564260 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5409. Min Act: -0.1700

Data Index: 884327 (Open Web Text)

Max Activating Token Index: 157

Text #13

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4841. Min Act: -0.1700

Data Index: 6004535 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4806. Min Act: -0.1700

Data Index: 5969807 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5113. Min Act: -0.1700

Data Index: 5672106 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4864. Min Act: -0.1700

Data Index: 3853361 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.5025. Min Act: -0.1700

Data Index: 7003227 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4751. Min Act: -0.1700

Data Index: 7490393 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 3.6491. Min Range: -3.6491

Max Act: 3.4880. Min Act: -0.1700

Data Index: 259275 (Open Web Text)

Max Activating Token Index: 274