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

Dataset: Open Web Text

Neuron 2444 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: 4.6302. Min Range: -4.6302

Max Act: 4.6302. Min Act: -0.1700

Data Index: 3765306 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.5862. Min Act: -0.1700

Data Index: 1116850 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.5476. Min Act: -0.1700

Data Index: 397701 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.5313. Min Act: -0.1700

Data Index: 6579329 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4775. Min Act: -0.1700

Data Index: 7468317 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.5547. Min Act: -0.1700

Data Index: 3200322 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.5135. Min Act: -0.1700

Data Index: 7538300 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4797. Min Act: -0.1700

Data Index: 8483954 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4707. Min Act: -0.1700

Data Index: 5112032 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4897. Min Act: -0.1700

Data Index: 4731512 (Open Web Text)

Max Activating Token Index: 219

Text #10

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4145. Min Act: -0.1700

Data Index: 4026144 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4298. Min Act: -0.1700

Data Index: 5568170 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4424. Min Act: -0.1700

Data Index: 426299 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4517. Min Act: -0.1700

Data Index: 4375531 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4416. Min Act: -0.1700

Data Index: 165467 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4343. Min Act: -0.1700

Data Index: 6944867 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4482. Min Act: -0.1700

Data Index: 4494441 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4089. Min Act: -0.1700

Data Index: 3371853 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4329. Min Act: -0.1700

Data Index: 1308773 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 4.6302. Min Range: -4.6302

Max Act: 4.4116. Min Act: -0.1700

Data Index: 1266267 (Open Web Text)

Max Activating Token Index: 1023