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

Dataset: Open Web Text

Neuron 838 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: 4.6805. Min Range: -4.6805

Max Act: 4.6805. Min Act: -0.1700

Data Index: 3758490 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.6217. Min Act: -0.1700

Data Index: 8136301 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.5395. Min Act: -0.1700

Data Index: 646987 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.5381. Min Act: -0.1700

Data Index: 2369003 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4686. Min Act: -0.1700

Data Index: 1427376 (Open Web Text)

Max Activating Token Index: 800

Text #5

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4990. Min Act: -0.1700

Data Index: 2204045 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4756. Min Act: -0.1700

Data Index: 6768574 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4500. Min Act: -0.1700

Data Index: 3542579 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4170. Min Act: -0.1700

Data Index: 6880052 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4224. Min Act: -0.1700

Data Index: 1215780 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4847. Min Act: -0.1700

Data Index: 6036913 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4693. Min Act: -0.1700

Data Index: 8761359 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4457. Min Act: -0.1700

Data Index: 5690170 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4334. Min Act: -0.1700

Data Index: 2901120 (Open Web Text)

Max Activating Token Index: 548

Text #14

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4661. Min Act: -0.1700

Data Index: 1522322 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4100. Min Act: -0.1700

Data Index: 3929098 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4095. Min Act: -0.1700

Data Index: 639542 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4150. Min Act: -0.1700

Data Index: 1176289 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4222. Min Act: -0.1700

Data Index: 333420 (Open Web Text)

Max Activating Token Index: 234

Text #19

Max Range: 4.6805. Min Range: -4.6805

Max Act: 4.4333. Min Act: -0.1700

Data Index: 6837393 (Open Web Text)

Max Activating Token Index: 552