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

Dataset: Open Web Text

Neuron 973 in Layer 6

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: 4.6679. Min Range: -4.6679

Max Act: 4.6679. Min Act: -0.1700

Data Index: 3210094 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.6324. Min Act: -0.1700

Data Index: 5161533 (Open Web Text)

Max Activating Token Index: 948

Text #2

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.6076. Min Act: -0.1700

Data Index: 5532249 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.5459. Min Act: -0.1700

Data Index: 702357 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.5239. Min Act: -0.1700

Data Index: 1256597 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.5263. Min Act: -0.1700

Data Index: 6254263 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4959. Min Act: -0.1700

Data Index: 2806992 (Open Web Text)

Max Activating Token Index: 308

Text #7

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.5084. Min Act: -0.1700

Data Index: 8352833 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4685. Min Act: -0.1700

Data Index: 2886179 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4640. Min Act: -0.1700

Data Index: 6438129 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4299. Min Act: -0.1700

Data Index: 4569928 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4471. Min Act: -0.1700

Data Index: 2292575 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4234. Min Act: -0.1700

Data Index: 8155003 (Open Web Text)

Max Activating Token Index: 932

Text #13

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.3853. Min Act: -0.1700

Data Index: 5946688 (Open Web Text)

Max Activating Token Index: 670

Text #14

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4293. Min Act: -0.1700

Data Index: 186363 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4332. Min Act: -0.1700

Data Index: 579157 (Open Web Text)

Max Activating Token Index: 295

Text #16

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4535. Min Act: -0.1700

Data Index: 7028963 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4407. Min Act: -0.1700

Data Index: 1158642 (Open Web Text)

Max Activating Token Index: 673

Text #18

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4172. Min Act: -0.1700

Data Index: 6948677 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.4355. Min Act: -0.1700

Data Index: 6927081 (Open Web Text)

Max Activating Token Index: 879