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

Dataset: Open Web Text

Neuron 617 in Layer 0

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: 4.5420. Min Range: -4.5420

Max Act: 4.5219. Min Act: -0.1700

Data Index: 4564327 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.5420. Min Act: -0.1700

Data Index: 3516666 (Open Web Text)

Max Activating Token Index: 889

Text #2

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4931. Min Act: -0.1700

Data Index: 4894638 (Open Web Text)

Max Activating Token Index: 306

Text #3

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4663. Min Act: -0.1700

Data Index: 1136293 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4608. Min Act: -0.1700

Data Index: 3516668 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4663. Min Act: -0.1700

Data Index: 6494579 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4179. Min Act: -0.1700

Data Index: 4425012 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4387. Min Act: -0.1700

Data Index: 3745084 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4322. Min Act: -0.1700

Data Index: 1198052 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4300. Min Act: -0.1700

Data Index: 8647419 (Open Web Text)

Max Activating Token Index: 311

Text #10

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4320. Min Act: -0.1700

Data Index: 7753823 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4209. Min Act: -0.1700

Data Index: 267191 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4395. Min Act: -0.1700

Data Index: 639803 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4297. Min Act: -0.1700

Data Index: 184598 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4360. Min Act: -0.1700

Data Index: 4457737 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4104. Min Act: -0.1700

Data Index: 3942305 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4029. Min Act: -0.1700

Data Index: 3598345 (Open Web Text)

Max Activating Token Index: 298

Text #17

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4023. Min Act: -0.1700

Data Index: 1468567 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4060. Min Act: -0.1700

Data Index: 113188 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 4.5420. Min Range: -4.5420

Max Act: 4.4171. Min Act: -0.1700

Data Index: 3040991 (Open Web Text)

Max Activating Token Index: 336