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

Dataset: Open Web Text

Neuron 1917 in Layer 4

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: 3.8193. Min Range: -3.8193

Max Act: 3.8193. Min Act: -0.1700

Data Index: 6826737 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7851. Min Act: -0.1700

Data Index: 249398 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7975. Min Act: -0.1700

Data Index: 6187792 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7847. Min Act: -0.1700

Data Index: 7266342 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7641. Min Act: -0.1700

Data Index: 7769286 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7715. Min Act: -0.1700

Data Index: 6428726 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7324. Min Act: -0.1700

Data Index: 2943133 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7297. Min Act: -0.1700

Data Index: 7676467 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7553. Min Act: -0.1700

Data Index: 3653342 (Open Web Text)

Max Activating Token Index: 827

Text #9

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7685. Min Act: -0.1700

Data Index: 4702048 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7224. Min Act: -0.1700

Data Index: 5304906 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7350. Min Act: -0.1700

Data Index: 5251164 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1464086 (Open Web Text)

Max Activating Token Index: 390

Text #13

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7172. Min Act: -0.1700

Data Index: 6971013 (Open Web Text)

Max Activating Token Index: 597

Text #14

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7341. Min Act: -0.1700

Data Index: 6304311 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7000. Min Act: -0.1700

Data Index: 2437296 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.7051. Min Act: -0.1700

Data Index: 5334654 (Open Web Text)

Max Activating Token Index: 219

Text #17

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6812. Min Act: -0.1700

Data Index: 1846714 (Open Web Text)

Max Activating Token Index: 348

Text #18

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6772. Min Act: -0.1700

Data Index: 1464058 (Open Web Text)

Max Activating Token Index: 577

Text #19

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6753. Min Act: -0.1700

Data Index: 4677803 (Open Web Text)

Max Activating Token Index: 997