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

Dataset: Open Web Text

Neuron 636 in Layer 3

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: 4.9942. Min Range: -4.9942

Max Act: 4.9942. Min Act: -0.1700

Data Index: 875559 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.8657. Min Act: -0.1700

Data Index: 5417701 (Open Web Text)

Max Activating Token Index: 168

Text #2

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7464. Min Act: -0.1700

Data Index: 2027603 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7443. Min Act: -0.1700

Data Index: 1646831 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7413. Min Act: -0.1700

Data Index: 5754750 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1255414 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7176. Min Act: -0.1700

Data Index: 3626734 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6829. Min Act: -0.1700

Data Index: 5045374 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.7002. Min Act: -0.1700

Data Index: 16551 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6778. Min Act: -0.1700

Data Index: 8669697 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6428. Min Act: -0.1700

Data Index: 7749257 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6573. Min Act: -0.1700

Data Index: 5059728 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6192. Min Act: -0.1700

Data Index: 710214 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6285. Min Act: -0.1700

Data Index: 4005209 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6299. Min Act: -0.1700

Data Index: 7707545 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6013. Min Act: -0.1700

Data Index: 6768034 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.5928. Min Act: -0.1700

Data Index: 8686736 (Open Web Text)

Max Activating Token Index: 197

Text #17

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.6044. Min Act: -0.1700

Data Index: 2370685 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.5822. Min Act: -0.1700

Data Index: 3296187 (Open Web Text)

Max Activating Token Index: 491

Text #19

Max Range: 4.9942. Min Range: -4.9942

Max Act: 4.5638. Min Act: -0.1700

Data Index: 2570279 (Open Web Text)

Max Activating Token Index: 797