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

Dataset: Open Web Text

Neuron 739 in Layer 0

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: 2.5121. Min Range: -2.5121

Max Act: 2.5121. Min Act: -0.1700

Data Index: 6834676 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.5099. Min Act: -0.1700

Data Index: 6781281 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.5032. Min Act: -0.1700

Data Index: 1762591 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4798. Min Act: -0.1700

Data Index: 6870160 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4927. Min Act: -0.1700

Data Index: 4696638 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4553. Min Act: -0.1700

Data Index: 5503987 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4561. Min Act: -0.1700

Data Index: 7376542 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4644. Min Act: -0.1700

Data Index: 366106 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4468. Min Act: -0.1700

Data Index: 3578040 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4423. Min Act: -0.1700

Data Index: 6245817 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4441. Min Act: -0.1700

Data Index: 1287958 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4524. Min Act: -0.1700

Data Index: 3578041 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4520. Min Act: -0.1700

Data Index: 5905110 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4453. Min Act: -0.1700

Data Index: 3689253 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4403. Min Act: -0.1700

Data Index: 8123878 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4460. Min Act: -0.1700

Data Index: 5307155 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4252. Min Act: -0.1700

Data Index: 5898494 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4323. Min Act: -0.1700

Data Index: 7197520 (Open Web Text)

Max Activating Token Index: 625

Text #18

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4375. Min Act: -0.1700

Data Index: 1643598 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 2.5121. Min Range: -2.5121

Max Act: 2.4152. Min Act: -0.1700

Data Index: 4549040 (Open Web Text)

Max Activating Token Index: 468