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

Dataset: Open Web Text

Neuron 979 in Layer 5

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: 3.1994. Min Range: -3.1994

Max Act: 3.1994. Min Act: -0.1700

Data Index: 8707075 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1763. Min Act: -0.1700

Data Index: 2710535 (Open Web Text)

Max Activating Token Index: 659

Text #2

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1753. Min Act: -0.1700

Data Index: 2710536 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1677. Min Act: -0.1700

Data Index: 6500703 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1707. Min Act: -0.1700

Data Index: 3897661 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1677. Min Act: -0.1700

Data Index: 689277 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1709. Min Act: -0.1700

Data Index: 2873580 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1555. Min Act: -0.1700

Data Index: 7985638 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1545. Min Act: -0.1700

Data Index: 5953198 (Open Web Text)

Max Activating Token Index: 712

Text #9

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1477. Min Act: -0.1700

Data Index: 1045392 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1249. Min Act: -0.1700

Data Index: 1018707 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1197. Min Act: -0.1700

Data Index: 4098135 (Open Web Text)

Max Activating Token Index: 886

Text #12

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1409. Min Act: -0.1700

Data Index: 3140254 (Open Web Text)

Max Activating Token Index: 230

Text #13

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1185. Min Act: -0.1700

Data Index: 7152015 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1063. Min Act: -0.1700

Data Index: 3700395 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.0869. Min Act: -0.1700

Data Index: 5011837 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1005. Min Act: -0.1700

Data Index: 3420364 (Open Web Text)

Max Activating Token Index: 317

Text #17

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.1006. Min Act: -0.1700

Data Index: 7686779 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.0844. Min Act: -0.1700

Data Index: 5038404 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 3.1994. Min Range: -3.1994

Max Act: 3.0963. Min Act: -0.1700

Data Index: 3617780 (Open Web Text)

Max Activating Token Index: 351