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

Dataset: Open Web Text

Neuron 2611 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: 2.0407. Min Range: -2.0407

Max Act: 2.0407. Min Act: -0.1693

Data Index: 3502014 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 2.0407. Min Range: -2.0407

Max Act: 2.0020. Min Act: -0.1700

Data Index: 1519700 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9626. Min Act: -0.1700

Data Index: 523243 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9628. Min Act: -0.1700

Data Index: 3523794 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9587. Min Act: -0.1700

Data Index: 4413595 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9563. Min Act: -0.1700

Data Index: 3134594 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9311. Min Act: -0.1700

Data Index: 6303209 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9428. Min Act: -0.1700

Data Index: 4351500 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9375. Min Act: -0.1697

Data Index: 2479013 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9261. Min Act: -0.1700

Data Index: 693999 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9195. Min Act: -0.1698

Data Index: 6409910 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9269. Min Act: -0.1700

Data Index: 217681 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9135. Min Act: -0.1700

Data Index: 41606 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9177. Min Act: -0.1691

Data Index: 1812700 (Open Web Text)

Max Activating Token Index: 978

Text #14

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9181. Min Act: -0.1700

Data Index: 6997813 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9277. Min Act: -0.1700

Data Index: 1362135 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8990. Min Act: -0.1700

Data Index: 8598372 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.9073. Min Act: -0.1700

Data Index: 8278849 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8802. Min Act: -0.1700

Data Index: 3164642 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.0407. Min Range: -2.0407

Max Act: 1.8888. Min Act: -0.1700

Data Index: 885582 (Open Web Text)

Max Activating Token Index: 774