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

Dataset: Open Web Text

Neuron 369 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: 5.5760. Min Range: -5.5760

Max Act: 5.5706. Min Act: -0.1700

Data Index: 3994492 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.5186. Min Act: -0.1695

Data Index: 1265875 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.5760. Min Act: -0.1700

Data Index: 5251227 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.5331. Min Act: -0.1697

Data Index: 6595992 (Open Web Text)

Max Activating Token Index: 177

Text #4

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4602. Min Act: -0.1700

Data Index: 5106151 (Open Web Text)

Max Activating Token Index: 584

Text #5

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4692. Min Act: -0.1700

Data Index: 8491872 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4310. Min Act: -0.1698

Data Index: 2216116 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4387. Min Act: -0.1700

Data Index: 1676285 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3924. Min Act: -0.1700

Data Index: 1574370 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4149. Min Act: -0.1700

Data Index: 4931784 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4102. Min Act: -0.1700

Data Index: 3268298 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3823. Min Act: -0.1700

Data Index: 5832640 (Open Web Text)

Max Activating Token Index: 258

Text #12

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3449. Min Act: -0.1700

Data Index: 3478204 (Open Web Text)

Max Activating Token Index: 525

Text #13

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4083. Min Act: -0.1695

Data Index: 6108659 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3925. Min Act: -0.1700

Data Index: 5808920 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.4038. Min Act: -0.1700

Data Index: 8421651 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3777. Min Act: -0.1700

Data Index: 7102204 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3932. Min Act: -0.1700

Data Index: 2741994 (Open Web Text)

Max Activating Token Index: 114

Text #18

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3587. Min Act: -0.1700

Data Index: 7081098 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 5.5760. Min Range: -5.5760

Max Act: 5.3599. Min Act: -0.1700

Data Index: 4639372 (Open Web Text)

Max Activating Token Index: 128