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

Dataset: Open Web Text

Neuron 825 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: 3.4328. Min Range: -3.4328

Max Act: 3.4328. Min Act: -0.1700

Data Index: 1502642 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3689. Min Act: -0.1700

Data Index: 2637973 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3654. Min Act: -0.1700

Data Index: 5641479 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3129. Min Act: -0.1700

Data Index: 6794821 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2920. Min Act: -0.1700

Data Index: 7558283 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3081. Min Act: -0.1700

Data Index: 590755 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3294. Min Act: -0.1700

Data Index: 6392236 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3118. Min Act: -0.1700

Data Index: 4213191 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2626. Min Act: -0.1700

Data Index: 616066 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2972. Min Act: -0.1700

Data Index: 7242929 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2686. Min Act: -0.1700

Data Index: 153272 (Open Web Text)

Max Activating Token Index: 910

Text #11

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3242. Min Act: -0.1700

Data Index: 5881646 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.3145. Min Act: -0.1700

Data Index: 5680780 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2745. Min Act: -0.1700

Data Index: 524705 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2014. Min Act: -0.1700

Data Index: 2021809 (Open Web Text)

Max Activating Token Index: 830

Text #15

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 76051 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2439. Min Act: -0.1700

Data Index: 5743502 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2734. Min Act: -0.1700

Data Index: 3898520 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2531. Min Act: -0.1700

Data Index: 4631871 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 3.4328. Min Range: -3.4328

Max Act: 3.2236. Min Act: -0.1700

Data Index: 3339223 (Open Web Text)

Max Activating Token Index: 900