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

Dataset: Open Web Text

Neuron 2274 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: 4.2237. Min Range: -4.2237

Max Act: 4.2237. Min Act: -0.1700

Data Index: 8602440 (Open Web Text)

Max Activating Token Index: 205

Text #1

Max Range: 4.2237. Min Range: -4.2237

Max Act: 4.1766. Min Act: -0.1700

Data Index: 6923474 (Open Web Text)

Max Activating Token Index: 729

Text #2

Max Range: 4.2237. Min Range: -4.2237

Max Act: 4.1525. Min Act: -0.1700

Data Index: 93333 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 4.2237. Min Range: -4.2237

Max Act: 4.0769. Min Act: -0.1700

Data Index: 6616415 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 4.2237. Min Range: -4.2237

Max Act: 4.0958. Min Act: -0.1700

Data Index: 6523801 (Open Web Text)

Max Activating Token Index: 159

Text #5

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9930. Min Act: -0.1700

Data Index: 3112726 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9922. Min Act: -0.1700

Data Index: 4506163 (Open Web Text)

Max Activating Token Index: 312

Text #7

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9497. Min Act: -0.1700

Data Index: 293235 (Open Web Text)

Max Activating Token Index: 857

Text #8

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9349. Min Act: -0.1700

Data Index: 7154960 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 4.2237. Min Range: -4.2237

Max Act: 4.0109. Min Act: -0.1700

Data Index: 3328008 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9678. Min Act: -0.1700

Data Index: 4368411 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9703. Min Act: -0.1700

Data Index: 4962187 (Open Web Text)

Max Activating Token Index: 692

Text #12

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9202. Min Act: -0.1700

Data Index: 8242379 (Open Web Text)

Max Activating Token Index: 161

Text #13

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9222. Min Act: -0.1700

Data Index: 5530131 (Open Web Text)

Max Activating Token Index: 912

Text #14

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9029. Min Act: -0.1700

Data Index: 1998195 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.8834. Min Act: -0.1700

Data Index: 5342166 (Open Web Text)

Max Activating Token Index: 98

Text #16

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.8981. Min Act: -0.1700

Data Index: 151862 (Open Web Text)

Max Activating Token Index: 319

Text #17

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.9122. Min Act: -0.1700

Data Index: 2181481 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.8407. Min Act: -0.1700

Data Index: 3847568 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 4.2237. Min Range: -4.2237

Max Act: 3.8702. Min Act: -0.1700

Data Index: 7126805 (Open Web Text)

Max Activating Token Index: 686