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

Dataset: Open Web Text

Neuron 985 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: 4.9257. Min Range: -4.9257

Max Act: 4.9257. Min Act: -0.1700

Data Index: 1162450 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.6845. Min Act: -0.1700

Data Index: 3608473 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.6278. Min Act: -0.1700

Data Index: 8746208 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.6240. Min Act: -0.1700

Data Index: 4667698 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5656. Min Act: -0.1700

Data Index: 2364739 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5751. Min Act: -0.1700

Data Index: 2062957 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5645. Min Act: -0.1700

Data Index: 5791669 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4799. Min Act: -0.1700

Data Index: 1820336 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5131. Min Act: -0.1700

Data Index: 8263782 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5107. Min Act: -0.1700

Data Index: 7891970 (Open Web Text)

Max Activating Token Index: 633

Text #10

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5029. Min Act: -0.1700

Data Index: 1151860 (Open Web Text)

Max Activating Token Index: 832

Text #11

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5173. Min Act: -0.1700

Data Index: 6566401 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.5127. Min Act: -0.1700

Data Index: 2444879 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4909. Min Act: -0.1700

Data Index: 6113465 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4887. Min Act: -0.1700

Data Index: 7449012 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4879. Min Act: -0.1700

Data Index: 6302273 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4467. Min Act: -0.1700

Data Index: 5349699 (Open Web Text)

Max Activating Token Index: 167

Text #17

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4875. Min Act: -0.1700

Data Index: 6401657 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4405. Min Act: -0.1700

Data Index: 4971233 (Open Web Text)

Max Activating Token Index: 198

Text #19

Max Range: 4.9257. Min Range: -4.9257

Max Act: 4.4964. Min Act: -0.1700

Data Index: 1230951 (Open Web Text)

Max Activating Token Index: 167