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

Dataset: Open Web Text

Neuron 259 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: 4.9190. Min Range: -4.9190

Max Act: 4.9190. Min Act: -0.1700

Data Index: 5732890 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.9185. Min Act: -0.1700

Data Index: 5220822 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.9124. Min Act: -0.1700

Data Index: 6205940 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8614. Min Act: -0.1700

Data Index: 3394395 (Open Web Text)

Max Activating Token Index: 1016

Text #4

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8149. Min Act: -0.1700

Data Index: 5049184 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8306. Min Act: -0.1700

Data Index: 8635026 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8490. Min Act: -0.1700

Data Index: 6466941 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8119. Min Act: -0.1700

Data Index: 8666042 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8001. Min Act: -0.1700

Data Index: 7787150 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8015. Min Act: -0.1700

Data Index: 1173568 (Open Web Text)

Max Activating Token Index: 178

Text #10

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8155. Min Act: -0.1700

Data Index: 6229277 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7924. Min Act: -0.1700

Data Index: 5965087 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7972. Min Act: -0.1700

Data Index: 1618124 (Open Web Text)

Max Activating Token Index: 975

Text #13

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7604. Min Act: -0.1700

Data Index: 1357158 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7643. Min Act: -0.1700

Data Index: 597022 (Open Web Text)

Max Activating Token Index: 181

Text #15

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7638. Min Act: -0.1700

Data Index: 2985298 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7697. Min Act: -0.1700

Data Index: 2414910 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7785. Min Act: -0.1700

Data Index: 3397469 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7742. Min Act: -0.1700

Data Index: 5653591 (Open Web Text)

Max Activating Token Index: 1014

Text #19

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7913. Min Act: -0.1700

Data Index: 1700108 (Open Web Text)

Max Activating Token Index: 1022