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

Dataset: Open Web Text

Neuron 2861 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: 3.3028. Min Range: -3.3028

Max Act: 3.3028. Min Act: -0.1700

Data Index: 3451467 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2706. Min Act: -0.1700

Data Index: 5210936 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2926. Min Act: -0.1700

Data Index: 8285269 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2719. Min Act: -0.1700

Data Index: 8157718 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2908. Min Act: -0.1700

Data Index: 2251491 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2470. Min Act: -0.1700

Data Index: 7581801 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2503. Min Act: -0.1700

Data Index: 4954365 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2375. Min Act: -0.1700

Data Index: 8529328 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2560. Min Act: -0.1700

Data Index: 4422555 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2560. Min Act: -0.1700

Data Index: 63112 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2382. Min Act: -0.1700

Data Index: 3882544 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2455. Min Act: -0.1700

Data Index: 3743596 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2560. Min Act: -0.1700

Data Index: 220921 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2347. Min Act: -0.1700

Data Index: 3498851 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2560. Min Act: -0.1700

Data Index: 693630 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2405. Min Act: -0.1700

Data Index: 6565443 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2646. Min Act: -0.1700

Data Index: 1496960 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2560. Min Act: -0.1700

Data Index: 6056101 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2623. Min Act: -0.1700

Data Index: 5513983 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.2468. Min Act: -0.1700

Data Index: 1146437 (Open Web Text)

Max Activating Token Index: 852