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

Dataset: Open Web Text

Neuron 983 in Layer 3

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: 3.9969. Min Range: -3.9969

Max Act: 3.9969. Min Act: -0.1700

Data Index: 2961991 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9239. Min Act: -0.1700

Data Index: 3037161 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9275. Min Act: -0.1700

Data Index: 7024878 (Open Web Text)

Max Activating Token Index: 953

Text #3

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8872. Min Act: -0.1700

Data Index: 150888 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8602. Min Act: -0.1700

Data Index: 2930289 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8616. Min Act: -0.1700

Data Index: 145306 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8675. Min Act: -0.1700

Data Index: 2113374 (Open Web Text)

Max Activating Token Index: 971

Text #7

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8367. Min Act: -0.1700

Data Index: 3060316 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8505. Min Act: -0.1700

Data Index: 8538575 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8634. Min Act: -0.1700

Data Index: 4074725 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8568. Min Act: -0.1700

Data Index: 1925397 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8607. Min Act: -0.1700

Data Index: 1394099 (Open Web Text)

Max Activating Token Index: 797

Text #12

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8866. Min Act: -0.1700

Data Index: 3903592 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8339. Min Act: -0.1700

Data Index: 446211 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8237. Min Act: -0.1700

Data Index: 4453312 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8203. Min Act: -0.1700

Data Index: 102181 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8058. Min Act: -0.1700

Data Index: 1552552 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8244. Min Act: -0.1700

Data Index: 170976 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8249. Min Act: -0.1700

Data Index: 4291078 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8229. Min Act: -0.1700

Data Index: 4076390 (Open Web Text)

Max Activating Token Index: 154