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

Dataset: Open Web Text

Neuron 2957 in Layer 0

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: 2.5817. Min Range: -2.5817

Max Act: 2.5817. Min Act: -0.1700

Data Index: 1078360 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5522. Min Act: -0.1700

Data Index: 7331548 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5460. Min Act: -0.1700

Data Index: 8565759 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5390. Min Act: -0.1700

Data Index: 2349250 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5445. Min Act: -0.1700

Data Index: 3969593 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5264. Min Act: -0.1700

Data Index: 7868345 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5356. Min Act: -0.1700

Data Index: 1636893 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5204. Min Act: -0.1700

Data Index: 6129909 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5194. Min Act: -0.1700

Data Index: 6471952 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5067. Min Act: -0.1700

Data Index: 7350258 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5128. Min Act: -0.1700

Data Index: 4202112 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5162. Min Act: -0.1700

Data Index: 3001424 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5043. Min Act: -0.1700

Data Index: 5000151 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.5067. Min Act: -0.1700

Data Index: 3913421 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4876. Min Act: -0.1700

Data Index: 4363822 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4926. Min Act: -0.1700

Data Index: 216301 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4945. Min Act: -0.1700

Data Index: 6899823 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4864. Min Act: -0.1700

Data Index: 2782925 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4882. Min Act: -0.1700

Data Index: 1570857 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.4880. Min Act: -0.1700

Data Index: 4383103 (Open Web Text)

Max Activating Token Index: 2