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

Dataset: Open Web Text

Neuron 664 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: 2.7483. Min Range: -2.7483

Max Act: 2.7483. Min Act: -0.1700

Data Index: 7490516 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.7062. Min Act: -0.1700

Data Index: 476850 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6957. Min Act: -0.1700

Data Index: 2279801 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6766. Min Act: -0.1700

Data Index: 4399737 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6652. Min Act: -0.1700

Data Index: 6967003 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6681. Min Act: -0.1700

Data Index: 588573 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6463. Min Act: -0.1700

Data Index: 1028209 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6731. Min Act: -0.1700

Data Index: 336337 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6380. Min Act: -0.1700

Data Index: 3544475 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6293. Min Act: -0.1700

Data Index: 4298590 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6565. Min Act: -0.1700

Data Index: 6186298 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6333. Min Act: -0.1700

Data Index: 7382341 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6062. Min Act: -0.1700

Data Index: 7901390 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6346. Min Act: -0.1700

Data Index: 1423311 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6147. Min Act: -0.1700

Data Index: 7892427 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6450. Min Act: -0.1700

Data Index: 7615316 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6394. Min Act: -0.1700

Data Index: 3862243 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6128. Min Act: -0.1700

Data Index: 5534132 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6252. Min Act: -0.1700

Data Index: 5523891 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.7483. Min Range: -2.7483

Max Act: 2.6171. Min Act: -0.1700

Data Index: 13391 (Open Web Text)

Max Activating Token Index: 1023