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

Dataset: Open Web Text

Neuron 2688 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: 3.4837. Min Range: -3.4837

Max Act: 3.4837. Min Act: -0.1700

Data Index: 6737026 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.4288. Min Act: -0.1700

Data Index: 6323176 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.4201. Min Act: -0.1700

Data Index: 797326 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.4033. Min Act: -0.1700

Data Index: 1295684 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3954. Min Act: -0.1700

Data Index: 151453 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3913. Min Act: -0.1700

Data Index: 4812487 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3740. Min Act: -0.1700

Data Index: 3839919 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3710. Min Act: -0.1700

Data Index: 4766337 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3687. Min Act: -0.1700

Data Index: 4439346 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3714. Min Act: -0.1700

Data Index: 110096 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3633. Min Act: -0.1700

Data Index: 6232834 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3538. Min Act: -0.1700

Data Index: 2703622 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3503. Min Act: -0.1700

Data Index: 5073106 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3626. Min Act: -0.1700

Data Index: 3321635 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3361. Min Act: -0.1700

Data Index: 6256677 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3475. Min Act: -0.1700

Data Index: 3005701 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3444. Min Act: -0.1700

Data Index: 2232872 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3469. Min Act: -0.1700

Data Index: 1367711 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3452. Min Act: -0.1700

Data Index: 3931505 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.4837. Min Range: -3.4837

Max Act: 3.3475. Min Act: -0.1700

Data Index: 4719755 (Open Web Text)

Max Activating Token Index: 7