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

Dataset: Open Web Text

Neuron 1631 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: 2.9377. Min Range: -2.9377

Max Act: 2.9319. Min Act: -0.1700

Data Index: 7932498 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9377. Min Act: -0.1700

Data Index: 544058 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.9301. Min Act: -0.1700

Data Index: 1162034 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8983. Min Act: -0.1700

Data Index: 6331613 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8841. Min Act: -0.1700

Data Index: 5351506 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8768. Min Act: -0.1700

Data Index: 7879744 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8705. Min Act: -0.1700

Data Index: 6927961 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8816. Min Act: -0.1700

Data Index: 6902383 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8660. Min Act: -0.1700

Data Index: 1411565 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8660. Min Act: -0.1700

Data Index: 2067910 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8623. Min Act: -0.1700

Data Index: 8810857 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8483. Min Act: -0.1700

Data Index: 5089817 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8593. Min Act: -0.1700

Data Index: 2346880 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8482. Min Act: -0.1700

Data Index: 5332157 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8468. Min Act: -0.1700

Data Index: 2478939 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8469. Min Act: -0.1700

Data Index: 5013363 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8537. Min Act: -0.1700

Data Index: 4847692 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8482. Min Act: -0.1700

Data Index: 2165448 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8512. Min Act: -0.1700

Data Index: 6445953 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9377. Min Range: -2.9377

Max Act: 2.8599. Min Act: -0.1700

Data Index: 3701534 (Open Web Text)

Max Activating Token Index: 4