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

Dataset: Open Web Text

Neuron 1919 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: 4.8444. Min Range: -4.8444

Max Act: 4.8444. Min Act: -0.1700

Data Index: 2065223 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6746. Min Act: -0.1700

Data Index: 6937473 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6645. Min Act: -0.1700

Data Index: 3911288 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5885. Min Act: -0.1700

Data Index: 6991957 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6370. Min Act: -0.1700

Data Index: 7327620 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6275. Min Act: -0.1700

Data Index: 5595366 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5666. Min Act: -0.1700

Data Index: 571866 (Open Web Text)

Max Activating Token Index: 783

Text #7

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6377. Min Act: -0.1700

Data Index: 5887130 (Open Web Text)

Max Activating Token Index: 167

Text #8

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6141. Min Act: -0.1700

Data Index: 4601206 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6151. Min Act: -0.1700

Data Index: 7211952 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6827. Min Act: -0.1700

Data Index: 5606680 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5495. Min Act: -0.1700

Data Index: 8360108 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5940. Min Act: -0.1700

Data Index: 8203295 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5410. Min Act: -0.1700

Data Index: 2986945 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5494. Min Act: -0.1700

Data Index: 2831935 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5918. Min Act: -0.1700

Data Index: 3945219 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5650. Min Act: -0.1700

Data Index: 3527874 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5349. Min Act: -0.1700

Data Index: 3314275 (Open Web Text)

Max Activating Token Index: 780

Text #18

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.6073. Min Act: -0.1700

Data Index: 1986768 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.8444. Min Range: -4.8444

Max Act: 4.5601. Min Act: -0.1700

Data Index: 1608453 (Open Web Text)

Max Activating Token Index: 225