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

Dataset: Open Web Text

Neuron 1449 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: 4.0287. Min Range: -4.0287

Max Act: 4.0287. Min Act: -0.1700

Data Index: 3292336 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.9671. Min Act: -0.1700

Data Index: 1599067 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.9167. Min Act: -0.1700

Data Index: 6055425 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.9052. Min Act: -0.1700

Data Index: 7837163 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8500. Min Act: -0.1700

Data Index: 2690811 (Open Web Text)

Max Activating Token Index: 788

Text #5

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8172. Min Act: -0.1700

Data Index: 7855885 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8190. Min Act: -0.1700

Data Index: 937381 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8085. Min Act: -0.1700

Data Index: 3875745 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7843. Min Act: -0.1700

Data Index: 4206284 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8138. Min Act: -0.1700

Data Index: 3119609 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7977. Min Act: -0.1700

Data Index: 3001270 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.8061. Min Act: -0.1700

Data Index: 4923196 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7451. Min Act: -0.1700

Data Index: 6927830 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7827. Min Act: -0.1700

Data Index: 6155243 (Open Web Text)

Max Activating Token Index: 761

Text #14

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7877. Min Act: -0.1700

Data Index: 1352069 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7659. Min Act: -0.1700

Data Index: 6285938 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7729. Min Act: -0.1700

Data Index: 2313099 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7696. Min Act: -0.1700

Data Index: 8323007 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7578. Min Act: -0.1700

Data Index: 1502533 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 4.0287. Min Range: -4.0287

Max Act: 3.7215. Min Act: -0.1700

Data Index: 6580168 (Open Web Text)

Max Activating Token Index: 308