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

Dataset: Open Web Text

Neuron 937 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: 5.4048. Min Range: -5.4048

Max Act: 5.4048. Min Act: -0.1700

Data Index: 4017726 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 5.4048. Min Range: -5.4048

Max Act: 5.1996. Min Act: -0.1700

Data Index: 153143 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 5.4048. Min Range: -5.4048

Max Act: 5.0728. Min Act: -0.1700

Data Index: 3894970 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9817. Min Act: -0.1700

Data Index: 3123566 (Open Web Text)

Max Activating Token Index: 871

Text #4

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9666. Min Act: -0.1700

Data Index: 260985 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9800. Min Act: -0.1700

Data Index: 8501675 (Open Web Text)

Max Activating Token Index: 312

Text #6

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9579. Min Act: -0.1700

Data Index: 6386556 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9440. Min Act: -0.1700

Data Index: 6580808 (Open Web Text)

Max Activating Token Index: 988

Text #8

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9384. Min Act: -0.1700

Data Index: 7877717 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9397. Min Act: -0.1700

Data Index: 5256196 (Open Web Text)

Max Activating Token Index: 326

Text #10

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9348. Min Act: -0.1700

Data Index: 1973400 (Open Web Text)

Max Activating Token Index: 635

Text #11

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9436. Min Act: -0.1700

Data Index: 4214845 (Open Web Text)

Max Activating Token Index: 372

Text #12

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9350. Min Act: -0.1700

Data Index: 6372242 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9393. Min Act: -0.1700

Data Index: 1176468 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.8998. Min Act: -0.1700

Data Index: 6403732 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9136. Min Act: -0.1700

Data Index: 3324163 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9017. Min Act: -0.1700

Data Index: 6860354 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.8792. Min Act: -0.1700

Data Index: 6154904 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.9097. Min Act: -0.1700

Data Index: 5896937 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 5.4048. Min Range: -5.4048

Max Act: 4.8851. Min Act: -0.1700

Data Index: 8278677 (Open Web Text)

Max Activating Token Index: 932