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

Dataset: Open Web Text

Neuron 1154 in Layer 6

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: 4.0896. Min Range: -4.0896

Max Act: 4.0896. Min Act: -0.1700

Data Index: 665729 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1375380 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0322. Min Act: -0.1700

Data Index: 252612 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0094. Min Act: -0.1700

Data Index: 7508328 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.0896. Min Range: -4.0896

Max Act: 4.0070. Min Act: -0.1700

Data Index: 2410722 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9582. Min Act: -0.1700

Data Index: 5100181 (Open Web Text)

Max Activating Token Index: 235

Text #6

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9509. Min Act: -0.1700

Data Index: 4410325 (Open Web Text)

Max Activating Token Index: 937

Text #7

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9489. Min Act: -0.1700

Data Index: 7383890 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9298. Min Act: -0.1700

Data Index: 547280 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9122. Min Act: -0.1700

Data Index: 8052470 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9322. Min Act: -0.1700

Data Index: 613932 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9296. Min Act: -0.1700

Data Index: 4716177 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.8996. Min Act: -0.1700

Data Index: 6967782 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9309. Min Act: -0.1700

Data Index: 6092913 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9138. Min Act: -0.1700

Data Index: 1460268 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9269. Min Act: -0.1700

Data Index: 5549636 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9386. Min Act: -0.1700

Data Index: 2232989 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9121. Min Act: -0.1700

Data Index: 87 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.9019. Min Act: -0.1700

Data Index: 5385965 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 4.0896. Min Range: -4.0896

Max Act: 3.8825. Min Act: -0.1700

Data Index: 3317423 (Open Web Text)

Max Activating Token Index: 282