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

Dataset: Open Web Text

Neuron 397 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: 4.7764. Min Range: -4.7764

Max Act: 4.7446. Min Act: -0.1700

Data Index: 3887024 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.7764. Min Act: -0.1700

Data Index: 8678106 (Open Web Text)

Max Activating Token Index: 236

Text #2

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.7011. Min Act: -0.1700

Data Index: 7076114 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6841. Min Act: -0.1700

Data Index: 7894594 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6518. Min Act: -0.1700

Data Index: 5522030 (Open Web Text)

Max Activating Token Index: 474

Text #5

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.7163. Min Act: -0.1700

Data Index: 674326 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6131. Min Act: -0.1700

Data Index: 7265196 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6543. Min Act: -0.1700

Data Index: 7088372 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6717. Min Act: -0.1700

Data Index: 2941930 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6182. Min Act: -0.1700

Data Index: 6222294 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6311. Min Act: -0.1700

Data Index: 7538259 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5749. Min Act: -0.1700

Data Index: 5091690 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5654. Min Act: -0.1700

Data Index: 2829885 (Open Web Text)

Max Activating Token Index: 285

Text #13

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5008. Min Act: -0.1700

Data Index: 6806695 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5875. Min Act: -0.1700

Data Index: 4441283 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5917. Min Act: -0.1700

Data Index: 8447543 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5936. Min Act: -0.1700

Data Index: 4963613 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5545. Min Act: -0.1700

Data Index: 4906402 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5356. Min Act: -0.1700

Data Index: 883509 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5267. Min Act: -0.1700

Data Index: 469853 (Open Web Text)

Max Activating Token Index: 743