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

Dataset: Open Web Text

Neuron 69 in Layer 4

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: 3.2099. Min Range: -3.2099

Max Act: 3.2099. Min Act: -0.1700

Data Index: 4317536 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.1203. Min Act: -0.1700

Data Index: 80834 (Open Web Text)

Max Activating Token Index: 931

Text #2

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.1343. Min Act: -0.1700

Data Index: 7382171 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0674. Min Act: -0.1700

Data Index: 838871 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.1165. Min Act: -0.1700

Data Index: 6173566 (Open Web Text)

Max Activating Token Index: 541

Text #5

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0730. Min Act: -0.1700

Data Index: 8002360 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0423. Min Act: -0.1700

Data Index: 8051752 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0590. Min Act: -0.1700

Data Index: 3644920 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0695. Min Act: -0.1700

Data Index: 7744567 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0328. Min Act: -0.1700

Data Index: 849843 (Open Web Text)

Max Activating Token Index: 943

Text #10

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0347. Min Act: -0.1700

Data Index: 5597731 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0125. Min Act: -0.1700

Data Index: 4874940 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0401. Min Act: -0.1700

Data Index: 5948196 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0439. Min Act: -0.1700

Data Index: 2103623 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 3.2099. Min Range: -3.2099

Max Act: 2.9937. Min Act: -0.1700

Data Index: 5948195 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0056. Min Act: -0.1700

Data Index: 5948197 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0088. Min Act: -0.1700

Data Index: 3636272 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0257. Min Act: -0.1700

Data Index: 4498826 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0009. Min Act: -0.1700

Data Index: 4107758 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 3.2099. Min Range: -3.2099

Max Act: 3.0068. Min Act: -0.1700

Data Index: 4125039 (Open Web Text)

Max Activating Token Index: 112