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

Dataset: Open Web Text

Neuron 1421 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: 3.0114. Min Range: -3.0114

Max Act: 3.0114. Min Act: -0.1700

Data Index: 6401298 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8819. Min Act: -0.1700

Data Index: 3257186 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8798. Min Act: -0.1700

Data Index: 1294434 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8469. Min Act: -0.1700

Data Index: 3532321 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7856. Min Act: -0.1700

Data Index: 2984687 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7845. Min Act: -0.1700

Data Index: 828795 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7502. Min Act: -0.1700

Data Index: 6824263 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7365. Min Act: -0.1700

Data Index: 5613989 (Open Web Text)

Max Activating Token Index: 978

Text #8

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7256. Min Act: -0.1700

Data Index: 4234491 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7244. Min Act: -0.1700

Data Index: 680260 (Open Web Text)

Max Activating Token Index: 90

Text #10

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7165. Min Act: -0.1700

Data Index: 672680 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7038. Min Act: -0.1700

Data Index: 744662 (Open Web Text)

Max Activating Token Index: 961

Text #12

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7015. Min Act: -0.1700

Data Index: 1556482 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7135. Min Act: -0.1700

Data Index: 4891366 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6904. Min Act: -0.1700

Data Index: 1156088 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6927. Min Act: -0.1700

Data Index: 2700299 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6920. Min Act: -0.1700

Data Index: 5620124 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6700. Min Act: -0.1700

Data Index: 2610545 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6775. Min Act: -0.1700

Data Index: 3794933 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6569. Min Act: -0.1700

Data Index: 6435734 (Open Web Text)

Max Activating Token Index: 178