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

Dataset: Open Web Text

Neuron 2668 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: 2.0107. Min Range: -2.0107

Max Act: 2.0044. Min Act: -0.1700

Data Index: 4255649 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 2.0107. Min Range: -2.0107

Max Act: 2.0107. Min Act: -0.1700

Data Index: 6086389 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9923. Min Act: -0.1700

Data Index: 7399381 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9677. Min Act: -0.1700

Data Index: 1568166 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9455. Min Act: -0.1700

Data Index: 1051079 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9362. Min Act: -0.1700

Data Index: 2894030 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9411. Min Act: -0.1700

Data Index: 1528526 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9217. Min Act: -0.1700

Data Index: 5358180 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9223. Min Act: -0.1698

Data Index: 3421969 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9297. Min Act: -0.1700

Data Index: 7526324 (Open Web Text)

Max Activating Token Index: 697

Text #10

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9197. Min Act: -0.1700

Data Index: 2072483 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9208. Min Act: -0.1700

Data Index: 583645 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9173. Min Act: -0.1700

Data Index: 821139 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9201. Min Act: -0.1700

Data Index: 7198643 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9145. Min Act: -0.1700

Data Index: 6874489 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9060. Min Act: -0.1700

Data Index: 7318434 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9061. Min Act: -0.1700

Data Index: 1138694 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.8941. Min Act: -0.1700

Data Index: 8437504 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.8884. Min Act: -0.1700

Data Index: 3844682 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9037. Min Act: -0.1700

Data Index: 8810224 (Open Web Text)

Max Activating Token Index: 440