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

Dataset: Open Web Text

Neuron 2481 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: 3.8326. Min Range: -3.8326

Max Act: 3.8326. Min Act: -0.1700

Data Index: 7335995 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.8039. Min Act: -0.1700

Data Index: 6177904 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7671. Min Act: -0.1700

Data Index: 7387722 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7798. Min Act: -0.1700

Data Index: 8556231 (Open Web Text)

Max Activating Token Index: 222

Text #4

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7727. Min Act: -0.1700

Data Index: 7978088 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7420. Min Act: -0.1700

Data Index: 6862702 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7429. Min Act: -0.1700

Data Index: 105939 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7411. Min Act: -0.1700

Data Index: 332225 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.6870. Min Act: -0.1700

Data Index: 6879145 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7410. Min Act: -0.1700

Data Index: 1593552 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7021. Min Act: -0.1700

Data Index: 7355521 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7090. Min Act: -0.1700

Data Index: 4564253 (Open Web Text)

Max Activating Token Index: 212

Text #12

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.6911. Min Act: -0.1700

Data Index: 6545155 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7232. Min Act: -0.1700

Data Index: 282958 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7036. Min Act: -0.1700

Data Index: 7581487 (Open Web Text)

Max Activating Token Index: 857

Text #15

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7071. Min Act: -0.1700

Data Index: 7728490 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.6948. Min Act: -0.1700

Data Index: 4964478 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7137. Min Act: -0.1700

Data Index: 423586 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.6765. Min Act: -0.1700

Data Index: 7922874 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 3.8326. Min Range: -3.8326

Max Act: 3.7120. Min Act: -0.1700

Data Index: 3486535 (Open Web Text)

Max Activating Token Index: 284