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

Dataset: Open Web Text

Neuron 1379 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: 3.5348. Min Range: -3.5348

Max Act: 3.5348. Min Act: -0.1700

Data Index: 7386676 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.5212. Min Act: -0.1700

Data Index: 144605 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1189215 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4976. Min Act: -0.1700

Data Index: 1067029 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.5114. Min Act: -0.1700

Data Index: 3310591 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4883. Min Act: -0.1700

Data Index: 3498457 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4694. Min Act: -0.1700

Data Index: 6784724 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4426. Min Act: -0.1700

Data Index: 241510 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4586. Min Act: -0.1700

Data Index: 6595893 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4220. Min Act: -0.1700

Data Index: 4136560 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4216. Min Act: -0.1700

Data Index: 560026 (Open Web Text)

Max Activating Token Index: 462

Text #11

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3987. Min Act: -0.1700

Data Index: 4810204 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1179903 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3828. Min Act: -0.1700

Data Index: 1651871 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3517. Min Act: -0.1700

Data Index: 1065243 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3479. Min Act: -0.1700

Data Index: 6874775 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3569. Min Act: -0.1700

Data Index: 217394 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3521. Min Act: -0.1700

Data Index: 5623925 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3565. Min Act: -0.1700

Data Index: 852650 (Open Web Text)

Max Activating Token Index: 242

Text #19

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3442. Min Act: -0.1700

Data Index: 5187221 (Open Web Text)

Max Activating Token Index: 558