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

Dataset: Open Web Text

Neuron 148 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: 2.8870. Min Range: -2.8870

Max Act: 2.8870. Min Act: -0.1700

Data Index: 1946776 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8709. Min Act: -0.1700

Data Index: 1367176 (Open Web Text)

Max Activating Token Index: 981

Text #2

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8299. Min Act: -0.1700

Data Index: 6645534 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8275. Min Act: -0.1700

Data Index: 2289487 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8402. Min Act: -0.1700

Data Index: 3756864 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8253. Min Act: -0.1700

Data Index: 4407785 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8605. Min Act: -0.1700

Data Index: 1374116 (Open Web Text)

Max Activating Token Index: 994

Text #7

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8180. Min Act: -0.1700

Data Index: 2470237 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8088. Min Act: -0.1700

Data Index: 3756865 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.7976. Min Act: -0.1700

Data Index: 8389541 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8260. Min Act: -0.1700

Data Index: 519699 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8213. Min Act: -0.1700

Data Index: 6824367 (Open Web Text)

Max Activating Token Index: 159

Text #12

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8133. Min Act: -0.1700

Data Index: 1874285 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8055. Min Act: -0.1700

Data Index: 4349497 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.7989. Min Act: -0.1700

Data Index: 6563094 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.7978. Min Act: -0.1700

Data Index: 2097738 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8094. Min Act: -0.1700

Data Index: 1946775 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.7371. Min Act: -0.1700

Data Index: 4741255 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8056. Min Act: -0.1700

Data Index: 2556343 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 2.8870. Min Range: -2.8870

Max Act: 2.8024. Min Act: -0.1700

Data Index: 2556344 (Open Web Text)

Max Activating Token Index: 256