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

Dataset: Open Web Text

Neuron 2794 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: 4.8380. Min Range: -4.8380

Max Act: 4.8380. Min Act: -0.1700

Data Index: 4663953 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.7220. Min Act: -0.1700

Data Index: 7327257 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.6169. Min Act: -0.1700

Data Index: 3577834 (Open Web Text)

Max Activating Token Index: 506

Text #3

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5671. Min Act: -0.1700

Data Index: 1217857 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5150. Min Act: -0.1700

Data Index: 6269683 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5284. Min Act: -0.1700

Data Index: 2004483 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5177. Min Act: -0.1700

Data Index: 5346963 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5218. Min Act: -0.1700

Data Index: 4197962 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4901. Min Act: -0.1700

Data Index: 3733774 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5310. Min Act: -0.1700

Data Index: 8711713 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.5265. Min Act: -0.1700

Data Index: 4722431 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4863. Min Act: -0.1700

Data Index: 684701 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4947. Min Act: -0.1700

Data Index: 464558 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4547. Min Act: -0.1700

Data Index: 7975920 (Open Web Text)

Max Activating Token Index: 362

Text #14

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4662. Min Act: -0.1700

Data Index: 8101282 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4379. Min Act: -0.1700

Data Index: 5868247 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4121. Min Act: -0.1700

Data Index: 4956098 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4135. Min Act: -0.1700

Data Index: 8430946 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.4355. Min Act: -0.1700

Data Index: 7846500 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 4.8380. Min Range: -4.8380

Max Act: 4.3959. Min Act: -0.1700

Data Index: 1128723 (Open Web Text)

Max Activating Token Index: 890