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

Dataset: Open Web Text

Neuron 1181 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: 3.0927. Min Range: -3.0927

Max Act: 3.0927. Min Act: -0.1700

Data Index: 8285507 (Open Web Text)

Max Activating Token Index: 568

Text #1

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.9777. Min Act: -0.1700

Data Index: 7911465 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.9589. Min Act: -0.1700

Data Index: 984003 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.9449. Min Act: -0.1700

Data Index: 311376 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.9094. Min Act: -0.1700

Data Index: 7413266 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.9308. Min Act: -0.1700

Data Index: 8553277 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8852. Min Act: -0.1700

Data Index: 2969932 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8642. Min Act: -0.1700

Data Index: 2309395 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8571. Min Act: -0.1700

Data Index: 2199952 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8470. Min Act: -0.1700

Data Index: 4628566 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8670. Min Act: -0.1700

Data Index: 7413267 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8190. Min Act: -0.1700

Data Index: 7262896 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8223. Min Act: -0.1700

Data Index: 8347871 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8087. Min Act: -0.1700

Data Index: 2638702 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.7774. Min Act: -0.1700

Data Index: 6182683 (Open Web Text)

Max Activating Token Index: 969

Text #15

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8082. Min Act: -0.1700

Data Index: 1335800 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.7916. Min Act: -0.1700

Data Index: 1126074 (Open Web Text)

Max Activating Token Index: 192

Text #17

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.7943. Min Act: -0.1700

Data Index: 5423436 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.7894. Min Act: -0.1700

Data Index: 1505427 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 3.0927. Min Range: -3.0927

Max Act: 2.8005. Min Act: -0.1700

Data Index: 185983 (Open Web Text)

Max Activating Token Index: 159