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

Dataset: Open Web Text

Neuron 1648 in Layer 1

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: 4.5349. Min Range: -4.5349

Max Act: 4.5349. Min Act: -0.1700

Data Index: 7949819 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4940. Min Act: -0.1700

Data Index: 7727274 (Open Web Text)

Max Activating Token Index: 57

Text #2

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4910. Min Act: -0.1700

Data Index: 6874407 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4781. Min Act: -0.1700

Data Index: 4365579 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4609. Min Act: -0.1700

Data Index: 3471201 (Open Web Text)

Max Activating Token Index: 581

Text #5

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4578. Min Act: -0.1700

Data Index: 3106670 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4676. Min Act: -0.1700

Data Index: 4675267 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4398. Min Act: -0.1700

Data Index: 4916061 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4265. Min Act: -0.1700

Data Index: 2896290 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4172. Min Act: -0.1700

Data Index: 5416440 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4356. Min Act: -0.1700

Data Index: 2246255 (Open Web Text)

Max Activating Token Index: 1002

Text #11

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4234. Min Act: -0.1700

Data Index: 6130358 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4346. Min Act: -0.1700

Data Index: 790637 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4264. Min Act: -0.1700

Data Index: 6671689 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4374. Min Act: -0.1700

Data Index: 7138875 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4220. Min Act: -0.1700

Data Index: 2084678 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4388. Min Act: -0.1700

Data Index: 1780302 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4426. Min Act: -0.1700

Data Index: 517862 (Open Web Text)

Max Activating Token Index: 80

Text #18

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4201. Min Act: -0.1700

Data Index: 1051647 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 4.5349. Min Range: -4.5349

Max Act: 4.4245. Min Act: -0.1700

Data Index: 1041480 (Open Web Text)

Max Activating Token Index: 14