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

Dataset: Open Web Text

Neuron 2783 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: 1.8664. Min Range: -1.8664

Max Act: 1.8664. Min Act: -0.1700

Data Index: 6407518 (Open Web Text)

Max Activating Token Index: 769

Text #1

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.8150. Min Act: -0.1698

Data Index: 1538814 (Open Web Text)

Max Activating Token Index: 830

Text #2

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.8285. Min Act: -0.1700

Data Index: 1322531 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.8323. Min Act: -0.1700

Data Index: 3616371 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.8067. Min Act: -0.1700

Data Index: 8205452 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.8002. Min Act: -0.1698

Data Index: 7287236 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7807. Min Act: -0.1700

Data Index: 4100192 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7849. Min Act: -0.1700

Data Index: 4154901 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7777. Min Act: -0.1700

Data Index: 2920886 (Open Web Text)

Max Activating Token Index: 706

Text #9

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7804. Min Act: -0.1700

Data Index: 3233242 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7641. Min Act: -0.1700

Data Index: 5049205 (Open Web Text)

Max Activating Token Index: 307

Text #11

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7714. Min Act: -0.1700

Data Index: 2269757 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7726. Min Act: -0.1700

Data Index: 1603803 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7550. Min Act: -0.1700

Data Index: 7326376 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7557. Min Act: -0.1700

Data Index: 429462 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7539. Min Act: -0.1700

Data Index: 456106 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7504. Min Act: -0.1700

Data Index: 1214062 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7445. Min Act: -0.1700

Data Index: 5834052 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7518. Min Act: -0.1700

Data Index: 5724311 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.7378. Min Act: -0.1700

Data Index: 788257 (Open Web Text)

Max Activating Token Index: 40