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

Dataset: Open Web Text

Neuron 2667 in Layer 2

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: 4.0691. Min Range: -4.0691

Max Act: 4.0691. Min Act: -0.1700

Data Index: 2115897 (Open Web Text)

Max Activating Token Index: 330

Text #1

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.9390. Min Act: -0.1700

Data Index: 607356 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.9263. Min Act: -0.1700

Data Index: 4438512 (Open Web Text)

Max Activating Token Index: 584

Text #3

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8639. Min Act: -0.1700

Data Index: 1567589 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8286. Min Act: -0.1700

Data Index: 1960534 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8175. Min Act: -0.1700

Data Index: 5966222 (Open Web Text)

Max Activating Token Index: 81

Text #6

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8252. Min Act: -0.1700

Data Index: 3087109 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8097. Min Act: -0.1700

Data Index: 1735788 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.8061. Min Act: -0.1700

Data Index: 6600131 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7699. Min Act: -0.1700

Data Index: 1821367 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7675. Min Act: -0.1700

Data Index: 1090173 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7881. Min Act: -0.1700

Data Index: 3027641 (Open Web Text)

Max Activating Token Index: 186

Text #12

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7901. Min Act: -0.1700

Data Index: 2746077 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7726. Min Act: -0.1700

Data Index: 7650223 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7809. Min Act: -0.1700

Data Index: 6282016 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7826. Min Act: -0.1700

Data Index: 2256269 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7765. Min Act: -0.1700

Data Index: 5345622 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7579. Min Act: -0.1700

Data Index: 792078 (Open Web Text)

Max Activating Token Index: 358

Text #18

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7612. Min Act: -0.1700

Data Index: 2042582 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 4.0691. Min Range: -4.0691

Max Act: 3.7592. Min Act: -0.1700

Data Index: 4771948 (Open Web Text)

Max Activating Token Index: 314